{"data":[{"name":"qwen2.5_vl_3b_instruct","displayName":"Qwen2.5-VL-3B-Instruct","link":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":26.7204,"vsi_bench_128frames":26.5242,"mmsi_bench":28.6,"mindcube_tiny":37.6,"viewspatial":31.97,"site":33.14,"blink":48.66,"3dsrbench":43.46,"embspatial":62.28,"mmsi_video_bench":27.67,"omnispatial_(manual_cot)":41.1,"spar_bench":28.28,"vsi_debiased":23.53},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":29.9353,"object_abs_distance":20.5995,"object_counting":17.7168,"object_rel_direction_accuracy":42.1498,"object_rel_distance_accuracy":33.5211,"object_size_estimation":14.8478,"room_size_estimation":27.6736,"route_planning_accuracy":27.3196},"vsi_bench_128frames":{"obj_appearance_order_accuracy":24.9191,"object_abs_distance":27.8297,"object_counting":12.5841,"object_rel_direction_accuracy":34.812,"object_rel_distance_accuracy":29.5775,"object_size_estimation":27.2508,"room_size_estimation":26.3542,"route_planning_accuracy":28.866},"mmsi_bench":{"pos_cam_cam_accuracy":36.56,"pos_obj_obj_accuracy":30.85,"pos_reg_reg_accuracy":28.4,"pos_cam_obj_accuracy":26.74,"pos_obj_reg_accuracy":28.24,"pos_cam_reg_accuracy":31.33,"attr_meas_accuracy":31.25,"attr_appr_accuracy":16.67,"motion_cam_accuracy":16.22,"motion_obj_accuracy":35.53,"msr_accuracy":28.79},"mindcube_tiny":{"rotation_accuracy":33.5,"among_accuracy":35.93,"around_accuracy":44.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":40.83,"camera_perspective_object_view_orientation_accuracy":28.71,"person_perspective_object_view_orientation_accuracy":30.12,"person_perspective_relative_direction_accuracy":29.22,"person_perspective_scene_simulation_relative_direction_accuracy":24.43},"site":{"3d_information_understanding_caa":16.12,"counting_and_existence_caa":48.43,"movement_prediction_and_navigation_caa":12.41,"object_localization_and_positioning_caa":43.63,"spatial_relationship_reasoning_caa":56.3,"multiview_and_crossimage_reasoning_caa":8.53},"blink":{"art_style":57.26,"counting":68.33,"forensic_detection":32.58,"functional_correspondence":22.31,"iq_test":20,"jigsaw":46,"multi_view_reasoning":43.61,"object_localization":55.74,"relative_depth":74.19,"relative_reflectance":38.81,"semantic_correspondence":36.69,"spatial_relation":82.52,"visual_correspondence":45.35,"visual_similarity":65.19},"3dsrbench":{"height_higher":45.8,"location_above":54.48,"location_closer_to_camera":69.62,"location_next_to":47.2,"multi_object_closer_to":44,"multi_object_facing":44.51,"multi_object_parallel":23.6,"multi_object_same_direction":39.83,"multi_object_viewpoint_towards_object":14.58,"orientation_in_front_of":43.9,"orientation_on_the_left":34.38,"orientation_viewpoint":20.41},"embspatial":{"mp3d_accuracy":63.2,"ai2thor_accuracy":56.74,"scannet_accuracy":67.08},"mmsi_video_bench":{"instance_scene_attribute_accuracy":30.12,"instance_instance_spatial_relationship_accuracy":17.11,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":21.74,"camera_instance_spatial_relationship_accuracy":24.05,"camera_scene_spatial_relationship_accuracy":30,"camera_motion_accuracy":33.33,"instance_motion_accuracy":27.78,"interactive_motion_accuracy":29.63,"memoery_update_accuracy":29.41,"multi_view_integration_accuracy":24.29,"planning_accuracy":27.42,"prediction_accuracy":36.59},"omnispatial_(manual_cot)":{"manipulation_accuracy":58.11,"motion_analysis_accuracy":46.24,"traffic_analysis_accuracy":43.53,"localization_accuracy":45.71,"geospatial_strategy_accuracy":47.27,"pattern_recognition_accuracy":21.65,"geometric_reasoning_accuracy":23.87,"egocentric_accuracy":63.73,"allocentric_accuracy":36.44,"hypothetical_accuracy":36.14},"spar_bench":{"depth_prediction_oc":30.36,"depth_prediction_oc_mv":34.09,"depth_prediction_oo":20.03,"depth_prediction_oo_mv":16.29,"distance_prediction_oc":17.05,"distance_prediction_oc_mv":21.42,"distance_prediction_oo":30.44,"distance_prediction_oo_mv":22.69,"position_matching_accuracy":39.95,"camera_motion_infer_accuracy":25.75,"view_change_infer_vci_metric":9.87,"distance_infer_center_oo_accuracy":57.35,"distance_infer_center_oo_mv_accuracy":59.23,"obj_spatial_relation_oc_mv_accuracy":39.5,"obj_spatial_relation_oo_accuracy":29.67,"obj_spatial_relation_oo_mv_accuracy":19.11,"spatial_imagination_oc_accuracy":19.89,"spatial_imagination_oc_mv_accuracy":27.62,"spatial_imagination_oo_accuracy":19.54,"spatial_imagination_oo_mv_accuracy":25.77},"vsi_debiased":{"object_counting":19.17,"object_abs_distance":21.22,"object_size_estimation":24.27,"room_size_estimation":27.29,"object_rel_distance_accuracy":33.8,"object_rel_direction_accuracy":42.09,"route_planning_accuracy":27.32,"obj_appearance_order_accuracy":20.87}}},{"name":"spatial_mllm_subset_sft","displayName":"Spatial-MLLM-subset-sft","link":"https://huggingface.co/Diankun/Spatial-MLLM-subset-sft","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":46.33,"mmsi_bench":26.1,"mindcube_tiny":33.46,"viewspatial":34.66,"site":18.02,"blink":40.45,"3dsrbench":36.18,"embspatial":49.95,"mmsi_video_bench":22.6,"omnispatial_(manual_cot)":37.96,"spar_bench":35.31,"vsi_debiased":37.97},"subScores":{"vsi_bench":{"object_counting":66.67,"object_abs_distance":38.06,"object_size_estimation":63.65,"room_size_estimation":35.45,"object_rel_distance_accuracy":40.42,"object_rel_direction_accuracy":48.22,"route_planning_accuracy":32.99,"obj_appearance_order_accuracy":44.34},"mmsi_bench":{"pos_cam_cam_accuracy":24.73,"pos_obj_obj_accuracy":21.28,"pos_reg_reg_accuracy":28.4,"pos_cam_obj_accuracy":30.23,"pos_obj_reg_accuracy":29.41,"pos_cam_reg_accuracy":28.92,"attr_meas_accuracy":18.75,"attr_appr_accuracy":34.85,"motion_cam_accuracy":10.81,"motion_obj_accuracy":23.68,"msr_accuracy":29.8},"mindcube_tiny":{"rotation_accuracy":39,"among_accuracy":30.51,"around_accuracy":36},"viewspatial":{"camera_perspective_relative_direction_accuracy":34.97,"camera_perspective_object_view_orientation_accuracy":23.39,"person_perspective_object_view_orientation_accuracy":40.36,"person_perspective_relative_direction_accuracy":40.38,"person_perspective_scene_simulation_relative_direction_accuracy":34.57},"site":{"3d_information_understanding_caa":6.98,"counting_and_existence_caa":30.32,"movement_prediction_and_navigation_caa":10.92,"object_localization_and_positioning_caa":24.22,"spatial_relationship_reasoning_caa":19.98,"multiview_and_crossimage_reasoning_caa":7.32},"blink":{"art_style":47.01,"counting":40.83,"forensic_detection":21.97,"functional_correspondence":20.77,"iq_test":23.33,"jigsaw":54,"multi_view_reasoning":43.61,"object_localization":54.92,"relative_depth":63.71,"relative_reflectance":29.1,"semantic_correspondence":34.53,"spatial_relation":54.55,"visual_correspondence":35.47,"visual_similarity":46.67},"3dsrbench":{"height_higher":42.46,"location_above":41.33,"location_closer_to_camera":45.72,"location_next_to":46.02,"multi_object_closer_to":40.57,"multi_object_facing":60.98,"multi_object_parallel":36.87,"multi_object_same_direction":47.67,"multi_object_viewpoint_towards_object":5.25,"orientation_in_front_of":41.28,"orientation_on_the_left":3.72,"orientation_viewpoint":1.75},"embspatial":{"mp3d_accuracy":51.54,"ai2thor_accuracy":46.89,"scannet_accuracy":51.5},"omnispatial_(manual_cot)":{"manipulation_accuracy":47.3,"motion_analysis_accuracy":36.42,"traffic_analysis_accuracy":37.65,"localization_accuracy":41.9,"geospatial_strategy_accuracy":42.73,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":23.87,"egocentric_accuracy":54.9,"allocentric_accuracy":39.89,"hypothetical_accuracy":34.94},"vsi_debiased":{"object_counting":66.67,"object_abs_distance":38.06,"object_size_estimation":63.65,"room_size_estimation":35.45,"object_rel_distance_accuracy":40.42,"object_rel_direction_accuracy":48.22,"route_planning_accuracy":32.99,"obj_appearance_order_accuracy":44.34}}},{"name":"bagel_7b_mot","displayName":"BAGEL-7B-MoT","link":"https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":31.42,"mmsi_bench":31,"mindcube_tiny":34.71,"viewspatial":41.32,"site":37.02,"blink":63.65,"3dsrbench":50.24,"embspatial":73.1,"mmsi_video_bench":27.76,"omnispatial_(manual_cot)":41.68,"spar_bench":39.1,"vsi_debiased":29.01},"subScores":{"vsi_bench":{"object_counting":30.09,"object_abs_distance":29.17,"object_size_estimation":35.53,"room_size_estimation":25.76,"object_rel_distance_accuracy":34.93,"object_rel_direction_accuracy":41.37,"route_planning_accuracy":30.41,"obj_appearance_order_accuracy":24.11},"mmsi_bench":{"pos_cam_cam_accuracy":34.41,"pos_obj_obj_accuracy":35.11,"pos_reg_reg_accuracy":29.63,"pos_cam_obj_accuracy":32.56,"pos_obj_reg_accuracy":42.35,"pos_cam_reg_accuracy":31.33,"attr_meas_accuracy":34.38,"attr_appr_accuracy":21.21,"motion_cam_accuracy":18.92,"motion_obj_accuracy":27.63,"msr_accuracy":30.3},"mindcube_tiny":{"rotation_accuracy":34.5,"among_accuracy":31.36,"around_accuracy":42.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":48.28,"camera_perspective_object_view_orientation_accuracy":38.65,"person_perspective_object_view_orientation_accuracy":46.99,"person_perspective_relative_direction_accuracy":42.52,"person_perspective_scene_simulation_relative_direction_accuracy":26.52},"site":{"3d_information_understanding_caa":22.32,"counting_and_existence_caa":50.05,"movement_prediction_and_navigation_caa":10.79,"object_localization_and_positioning_caa":64.16,"spatial_relationship_reasoning_caa":63.24,"multiview_and_crossimage_reasoning_caa":4.29},"blink":{"art_style":78.63,"counting":75,"forensic_detection":37.88,"functional_correspondence":40,"iq_test":32,"jigsaw":85.33,"multi_view_reasoning":45.86,"object_localization":72.13,"relative_depth":89.52,"relative_reflectance":31.34,"semantic_correspondence":46.04,"spatial_relation":82.52,"visual_correspondence":81.98,"visual_similarity":92.59},"3dsrbench":{"height_higher":46.96,"location_above":64.02,"location_closer_to_camera":75.52,"location_next_to":49.56,"multi_object_closer_to":56.57,"multi_object_facing":58.09,"multi_object_parallel":48.97,"multi_object_same_direction":49.13,"multi_object_viewpoint_towards_object":4.96,"orientation_in_front_of":58.14,"orientation_on_the_left":29.23,"orientation_viewpoint":26.53},"embspatial":{"mp3d_accuracy":72.19,"ai2thor_accuracy":71.43,"scannet_accuracy":75.75},"mmsi_video_bench":{"instance_scene_attribute_accuracy":31.33,"instance_instance_spatial_relationship_accuracy":27.63,"instance_scene_spatial_relationship_accuracy":27.27,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":27.85,"camera_scene_spatial_relationship_accuracy":26.25,"camera_motion_accuracy":27.96,"instance_motion_accuracy":22.22,"interactive_motion_accuracy":27.16,"memoery_update_accuracy":34.31,"multi_view_integration_accuracy":31.43,"planning_accuracy":26.61,"prediction_accuracy":23.17},"omnispatial_(manual_cot)":{"manipulation_accuracy":59.46,"motion_analysis_accuracy":49.71,"traffic_analysis_accuracy":45.88,"localization_accuracy":52.38,"geospatial_strategy_accuracy":39.09,"pattern_recognition_accuracy":30.93,"geometric_reasoning_accuracy":23.87,"egocentric_accuracy":68.63,"allocentric_accuracy":32.18,"hypothetical_accuracy":33.73},"spar_bench":{"depth_prediction_oc":48.11,"depth_prediction_oc_mv":38.41,"depth_prediction_oo":19.52,"depth_prediction_oo_mv":22.34,"distance_prediction_oc":55.8,"distance_prediction_oc_mv":50.33,"distance_prediction_oo":15.37,"distance_prediction_oo_mv":26.5,"position_matching_accuracy":58.78,"camera_motion_infer_accuracy":32.5,"view_change_infer_vci_metric":15.12,"distance_infer_center_oo_accuracy":57.94,"distance_infer_center_oo_mv_accuracy":57.44,"obj_spatial_relation_oc_mv_accuracy":51.5,"obj_spatial_relation_oo_accuracy":57.69,"obj_spatial_relation_oo_mv_accuracy":35.73,"spatial_imagination_oc_accuracy":33.87,"spatial_imagination_oc_mv_accuracy":40.12,"spatial_imagination_oo_accuracy":28.81,"spatial_imagination_oo_mv_accuracy":36.13},"vsi_debiased":{"object_counting":30.09,"object_abs_distance":29.17,"object_size_estimation":35.53,"room_size_estimation":25.76,"object_rel_distance_accuracy":34.93,"object_rel_direction_accuracy":41.37,"route_planning_accuracy":30.41,"obj_appearance_order_accuracy":24.11}}},{"name":"mindcube_qwen2.5vl_rawqa_sft","displayName":"MindCube-Qwen2.5VL-RawQA-SFT","link":"https://huggingface.co/MLL-Lab/MindCube-Qwen2.5VL-RawQA-SFT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":17.24,"mmsi_bench":1.7,"mindcube_tiny":51.73,"viewspatial":24.14,"site":6.31,"blink":35.09,"3dsrbench":2.75,"embspatial":36.98,"mmsi_video_bench":5.15,"omnispatial_(manual_cot)":24.53,"spar_bench":20.8,"vsi_debiased":18.55},"subScores":{"vsi_bench":{"object_counting":12.88,"object_abs_distance":22.78,"object_size_estimation":4.33,"room_size_estimation":23.47,"object_rel_distance_accuracy":20.28,"object_rel_direction_accuracy":15.72,"route_planning_accuracy":15.98,"obj_appearance_order_accuracy":22.49},"mmsi_bench":{"pos_cam_cam_accuracy":0,"pos_obj_obj_accuracy":2.13,"pos_reg_reg_accuracy":2.47,"pos_cam_obj_accuracy":2.33,"pos_obj_reg_accuracy":2.35,"pos_cam_reg_accuracy":3.61,"attr_meas_accuracy":3.12,"attr_appr_accuracy":0,"motion_cam_accuracy":0,"motion_obj_accuracy":0,"msr_accuracy":2.02},"mindcube_tiny":{"rotation_accuracy":34,"among_accuracy":51.02,"around_accuracy":67.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":30.85,"camera_perspective_object_view_orientation_accuracy":22.09,"person_perspective_object_view_orientation_accuracy":23.69,"person_perspective_relative_direction_accuracy":22.45,"person_perspective_scene_simulation_relative_direction_accuracy":16.92},"site":{"3d_information_understanding_caa":-6.9,"counting_and_existence_caa":20.78,"movement_prediction_and_navigation_caa":-8.86,"object_localization_and_positioning_caa":10.62,"spatial_relationship_reasoning_caa":15.9,"multiview_and_crossimage_reasoning_caa":-6.8},"blink":{"art_style":52.99,"counting":36.67,"forensic_detection":26.52,"functional_correspondence":6.92,"iq_test":26,"jigsaw":47.33,"multi_view_reasoning":55.64,"object_localization":56.56,"relative_depth":41.13,"relative_reflectance":31.34,"semantic_correspondence":0,"spatial_relation":67.13,"visual_correspondence":3.49,"visual_similarity":51.11},"3dsrbench":{"height_higher":0,"location_above":12.28,"location_closer_to_camera":0,"location_next_to":5.31,"multi_object_closer_to":6.86,"multi_object_facing":4.34,"multi_object_parallel":0,"multi_object_same_direction":0,"multi_object_viewpoint_towards_object":0,"orientation_in_front_of":0,"orientation_on_the_left":0,"orientation_viewpoint":0},"embspatial":{"mp3d_accuracy":36.72,"ai2thor_accuracy":33.01,"scannet_accuracy":41.33},"mmsi_video_bench":{"instance_scene_attribute_accuracy":7.23,"instance_instance_spatial_relationship_accuracy":7.89,"instance_scene_spatial_relationship_accuracy":6.49,"scene_scene_spatial_relationship_accuracy":0,"camera_instance_spatial_relationship_accuracy":2.53,"camera_scene_spatial_relationship_accuracy":5,"camera_motion_accuracy":4.3,"instance_motion_accuracy":4.44,"interactive_motion_accuracy":11.11,"memoery_update_accuracy":3.92,"multi_view_integration_accuracy":2.86,"planning_accuracy":6.45,"prediction_accuracy":3.66},"omnispatial_(manual_cot)":{"manipulation_accuracy":20.27,"motion_analysis_accuracy":25.43,"traffic_analysis_accuracy":21.18,"localization_accuracy":23.81,"geospatial_strategy_accuracy":24.55,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":25.81,"egocentric_accuracy":21.57,"allocentric_accuracy":25.53,"hypothetical_accuracy":22.89},"spar_bench":{"depth_prediction_oc":26.92,"depth_prediction_oc_mv":16.97,"depth_prediction_oo":16.29,"depth_prediction_oo_mv":14.17,"distance_prediction_oc":13.97,"distance_prediction_oc_mv":12.03,"distance_prediction_oo":18.62,"distance_prediction_oo_mv":14.78,"position_matching_accuracy":22.39,"camera_motion_infer_accuracy":20.5,"view_change_infer_vci_metric":25,"distance_infer_center_oo_accuracy":30.88,"distance_infer_center_oo_mv_accuracy":15.48,"obj_spatial_relation_oc_mv_accuracy":24,"obj_spatial_relation_oo_accuracy":25.55,"obj_spatial_relation_oo_mv_accuracy":22.99,"spatial_imagination_oc_accuracy":25,"spatial_imagination_oc_mv_accuracy":23.84,"spatial_imagination_oo_accuracy":23.51,"spatial_imagination_oo_mv_accuracy":23.25},"vsi_debiased":{"object_counting":12.88,"object_abs_distance":22.78,"object_size_estimation":4.33,"room_size_estimation":23.47,"object_rel_distance_accuracy":20.28,"object_rel_direction_accuracy":15.72,"route_planning_accuracy":15.98,"obj_appearance_order_accuracy":22.49}}},{"name":"gemini_3_pro","displayName":"Gemini 3 Pro","link":"https://aistudio.google.com/prompts/new_chat?model=gemini-3-pro-preview","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":52.51,"mmsi_bench":45.2,"mindcube_tiny":70.87,"viewspatial":50.36,"site":62.25,"blink":76.01,"3dsrbench":68.92,"embspatial":84.29,"mmsi_video_bench":40.42,"omnispatial_(manual_cot)":69.14,"spar_bench":48.74,"vsi_debiased":53.78},"subScores":{"vsi_bench":{"object_counting":38,"object_abs_distance":37.76,"object_size_estimation":72.71,"room_size_estimation":44.13,"object_rel_distance_accuracy":59.86,"object_rel_direction_accuracy":55.74,"route_planning_accuracy":45.88,"obj_appearance_order_accuracy":66.02},"mmsi_bench":{"pos_cam_cam_accuracy":47.31,"pos_obj_obj_accuracy":48.94,"pos_reg_reg_accuracy":41.98,"pos_cam_obj_accuracy":43.02,"pos_obj_reg_accuracy":37.65,"pos_cam_reg_accuracy":60.24,"attr_meas_accuracy":64.06,"attr_appr_accuracy":39.39,"motion_cam_accuracy":41.89,"motion_obj_accuracy":47.37,"msr_accuracy":37.88},"mindcube_tiny":{"rotation_accuracy":93,"among_accuracy":60.68,"around_accuracy":77.2},"viewspatial":{"camera_perspective_relative_direction_accuracy":61.87,"camera_perspective_object_view_orientation_accuracy":31.63,"person_perspective_object_view_orientation_accuracy":41.06,"person_perspective_relative_direction_accuracy":74.35,"person_perspective_scene_simulation_relative_direction_accuracy":38.91},"site":{"3d_information_understanding_caa":55.12,"counting_and_existence_caa":65.65,"movement_prediction_and_navigation_caa":50.48,"object_localization_and_positioning_caa":80.88,"spatial_relationship_reasoning_caa":75.46,"multiview_and_crossimage_reasoning_caa":44.82},"blink":{"art_style":86.32,"counting":77.5,"forensic_detection":98.48,"functional_correspondence":66.92,"iq_test":42,"jigsaw":77.33,"multi_view_reasoning":57.89,"object_localization":85.25,"relative_depth":90.32,"relative_reflectance":32.09,"semantic_correspondence":72.66,"spatial_relation":93.01,"visual_correspondence":95.93,"visual_similarity":88.89},"3dsrbench":{"height_higher":68.99,"location_above":73.12,"location_closer_to_camera":80.09,"location_next_to":72.86,"multi_object_closer_to":74.86,"multi_object_facing":73.41,"multi_object_parallel":66.08,"multi_object_same_direction":63.37,"multi_object_viewpoint_towards_object":35.28,"orientation_in_front_of":82.27,"orientation_on_the_left":72.78,"orientation_viewpoint":48.4},"embspatial":{"mp3d_accuracy":83.35,"ai2thor_accuracy":84.5,"scannet_accuracy":85},"mmsi_video_bench":{"instance_scene_attribute_accuracy":49.4,"instance_instance_spatial_relationship_accuracy":43.42,"instance_scene_spatial_relationship_accuracy":49.35,"scene_scene_spatial_relationship_accuracy":34.78,"camera_instance_spatial_relationship_accuracy":37.97,"camera_scene_spatial_relationship_accuracy":46.25,"camera_motion_accuracy":37.63,"instance_motion_accuracy":41.11,"interactive_motion_accuracy":29.63,"memoery_update_accuracy":36.27,"multi_view_integration_accuracy":37.14,"planning_accuracy":44.35,"prediction_accuracy":36.59},"omnispatial_(manual_cot)":{"manipulation_accuracy":74.32,"motion_analysis_accuracy":74.86,"traffic_analysis_accuracy":72.94,"localization_accuracy":85.71,"geospatial_strategy_accuracy":79.09,"pattern_recognition_accuracy":60.82,"geometric_reasoning_accuracy":41.29,"egocentric_accuracy":87.25,"allocentric_accuracy":63.3,"hypothetical_accuracy":68.67},"spar_bench":{"depth_prediction_oc":52.97,"depth_prediction_oc_mv":37.09,"depth_prediction_oo":27.07,"depth_prediction_oo_mv":19.19,"distance_prediction_oc":57.33,"distance_prediction_oc_mv":49.32,"distance_prediction_oo":51.07,"distance_prediction_oo_mv":32.83,"position_matching_accuracy":61.58,"camera_motion_infer_accuracy":25.75,"view_change_infer_vci_metric":23.19,"distance_infer_center_oo_accuracy":78.53,"distance_infer_center_oo_mv_accuracy":76.79,"obj_spatial_relation_oc_mv_accuracy":61.25,"obj_spatial_relation_oo_accuracy":63.46,"obj_spatial_relation_oo_mv_accuracy":59.83,"spatial_imagination_oc_accuracy":57.26,"spatial_imagination_oc_mv_accuracy":52.91,"spatial_imagination_oo_accuracy":39.07,"spatial_imagination_oo_mv_accuracy":48.46},"vsi_debiased":{"object_counting":38,"object_abs_distance":37.76,"object_size_estimation":72.71,"room_size_estimation":44.13,"object_rel_distance_accuracy":59.86,"object_rel_direction_accuracy":55.74,"route_planning_accuracy":45.88,"obj_appearance_order_accuracy":66.02}}},{"name":"gemini_2.5_pro","displayName":"Gemini 2.5 Pro","link":"https://aistudio.google.com/prompts/new_chat?model=gemini-2.5-pro","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":53.57,"mmsi_bench":38,"mindcube_tiny":57.6,"viewspatial":46.06,"site":57.06,"blink":73.49,"3dsrbench":59.34,"embspatial":78.85,"mmsi_video_bench":32.91,"omnispatial_(manual_cot)":57.6,"spar_bench":49.75,"vsi_debiased":51.81},"subScores":{"vsi_bench":{"object_counting":46.04,"object_abs_distance":37.39,"object_size_estimation":68.72,"room_size_estimation":54.37,"object_rel_distance_accuracy":61.97,"object_rel_direction_accuracy":43.9,"route_planning_accuracy":47.42,"obj_appearance_order_accuracy":68.77},"mmsi_bench":{"pos_cam_cam_accuracy":38.71,"pos_obj_obj_accuracy":34.04,"pos_reg_reg_accuracy":40.74,"pos_cam_obj_accuracy":44.19,"pos_obj_reg_accuracy":38.82,"pos_cam_reg_accuracy":40.96,"attr_meas_accuracy":62.5,"attr_appr_accuracy":30.3,"motion_cam_accuracy":39.19,"motion_obj_accuracy":25,"msr_accuracy":33.33},"mindcube_tiny":{"rotation_accuracy":88,"among_accuracy":44.92,"around_accuracy":63.2},"viewspatial":{"camera_perspective_relative_direction_accuracy":59.11,"camera_perspective_object_view_orientation_accuracy":33.03,"person_perspective_object_view_orientation_accuracy":51,"person_perspective_relative_direction_accuracy":45.84,"person_perspective_scene_simulation_relative_direction_accuracy":32.58},"site":{"counting_and_existence_caa":61.31,"object_localization_and_positioning_caa":69.18,"3d_information_understanding_caa":55.17,"multiview_and_crossimage_reasoning_caa":38.52,"spatial_relationship_reasoning_caa":71.51,"movement_prediction_and_navigation_caa":48.62},"blink":{"art_style":86,"counting":78,"forensic_detection":90,"functional_correspondence":62,"iq_test":44,"jigsaw":85,"multi_view_reasoning":51,"object_localization":76,"relative_depth":86,"relative_reflectance":34,"semantic_correspondence":68,"spatial_relation":90,"visual_correspondence":91,"visual_similarity":86},"3dsrbench":{"height_higher":68.12,"location_above":66.33,"location_closer_to_camera":78.76,"location_next_to":81.12,"multi_object_closer_to":66.86,"multi_object_facing":63.29,"multi_object_parallel":56.93,"multi_object_same_direction":45.35,"multi_object_viewpoint_towards_object":15.16,"orientation_in_front_of":67.15,"orientation_on_the_left":31.23,"orientation_viewpoint":37.32},"embspatial":{"mp3d_accuracy":77.77,"ai2thor_accuracy":78.05,"scannet_accuracy":80.75},"omnispatial_(manual_cot)":{"manipulation_accuracy":62.16,"motion_analysis_accuracy":65.9,"traffic_analysis_accuracy":62.35,"localization_accuracy":78.1,"geospatial_strategy_accuracy":68.99,"pattern_recognition_accuracy":44.33,"geometric_reasoning_accuracy":31.61,"egocentric_accuracy":83.33,"allocentric_accuracy":40.43,"hypothetical_accuracy":42.17}}},{"name":"grok_4","displayName":"Grok 4","link":"https://x.ai/news/grok-4","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":47.92,"mmsi_bench":37.8,"mindcube_tiny":63.56,"viewspatial":43.23,"site":47.01,"blink":56.44,"3dsrbench":54.93,"embspatial":75.52,"mmsi_video_bench":27.22,"omnispatial_(manual_cot)":47.68,"spar_bench":44.76,"vsi_debiased":45.68},"subScores":{"vsi_bench":{"object_counting":37.17,"object_abs_distance":32.96,"object_size_estimation":60.82,"room_size_estimation":45.42,"object_rel_distance_accuracy":53.1,"object_rel_direction_accuracy":39.67,"route_planning_accuracy":47.42,"obj_appearance_order_accuracy":66.83},"mmsi_bench":{"pos_cam_cam_accuracy":36.56,"pos_obj_obj_accuracy":35.11,"pos_reg_reg_accuracy":39.51,"pos_cam_obj_accuracy":34.88,"pos_obj_reg_accuracy":45.88,"pos_cam_reg_accuracy":50.6,"attr_meas_accuracy":21.88,"attr_appr_accuracy":22.73,"motion_cam_accuracy":40.54,"motion_obj_accuracy":43.42,"msr_accuracy":38.38},"mindcube_tiny":{"rotation_accuracy":93,"among_accuracy":54.41,"around_accuracy":61.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":57.13,"camera_perspective_object_view_orientation_accuracy":23.9,"person_perspective_object_view_orientation_accuracy":47.59,"person_perspective_relative_direction_accuracy":51.66,"person_perspective_scene_simulation_relative_direction_accuracy":24.89},"site":{"counting_and_existence_caa":50.44,"object_localization_and_positioning_caa":60.33,"3d_information_understanding_caa":51.57,"multiview_and_crossimage_reasoning_caa":26.21,"spatial_relationship_reasoning_caa":61.22,"movement_prediction_and_navigation_caa":37.42},"blink":{"art_style":82.05,"counting":65.83,"forensic_detection":78.79,"functional_correspondence":47.69,"iq_test":8,"jigsaw":60,"multi_view_reasoning":42.11,"object_localization":54.1,"relative_depth":68.55,"relative_reflectance":40.3,"semantic_correspondence":38.13,"spatial_relation":83.22,"visual_correspondence":47.67,"visual_similarity":85.19},"3dsrbench":{"height_higher":63.48,"location_above":68.64,"location_closer_to_camera":71.53,"location_next_to":66.08,"multi_object_closer_to":52.57,"multi_object_facing":61.56,"multi_object_parallel":46.31,"multi_object_same_direction":46.51,"multi_object_viewpoint_towards_object":21.87,"orientation_in_front_of":62.79,"orientation_on_the_left":36.39,"orientation_viewpoint":23.03},"embspatial":{"mp3d_accuracy":75.35,"ai2thor_accuracy":75.38,"scannet_accuracy":75.83},"omnispatial_(manual_cot)":{"manipulation_accuracy":59.46,"motion_analysis_accuracy":57.51,"traffic_analysis_accuracy":47.06,"localization_accuracy":46.67,"geospatial_strategy_accuracy":50,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":30.97,"egocentric_accuracy":73.53,"allocentric_accuracy":37.23,"hypothetical_accuracy":50.6}}},{"name":"gpt_5","displayName":"GPT-5","link":"https://openai.com/gpt-5/","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":55.03,"mmsi_bench":41.8,"mindcube_tiny":56.3,"viewspatial":45.59,"site":61.88,"blink":68.02,"3dsrbench":60.29,"embspatial":81.62,"mmsi_video_bench":33.36,"omnispatial_(manual_cot)":59.23,"spar_bench":49.74,"vsi_debiased":52.47},"subScores":{"vsi_bench":{"object_counting":53.31,"object_abs_distance":34.47,"object_size_estimation":73.31,"room_size_estimation":47.52,"object_rel_distance_accuracy":63.71,"object_rel_direction_accuracy":48.69,"route_planning_accuracy":50.26,"obj_appearance_order_accuracy":68.93},"mmsi_bench":{"pos_cam_cam_accuracy":41.94,"pos_obj_obj_accuracy":32.98,"pos_reg_reg_accuracy":35.8,"pos_cam_obj_accuracy":49.84,"pos_obj_reg_accuracy":42.35,"pos_cam_reg_accuracy":68.67,"attr_meas_accuracy":54.69,"attr_appr_accuracy":37.38,"motion_cam_accuracy":28.33,"motion_obj_accuracy":40.79,"msr_accuracy":36.36},"mindcube_tiny":{"rotation_accuracy":94.5,"among_accuracy":38.2,"around_accuracy":68.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":60.18,"camera_perspective_object_view_orientation_accuracy":27.91,"person_perspective_object_view_orientation_accuracy":40.96,"person_perspective_relative_direction_accuracy":48.46,"person_perspective_scene_simulation_relative_direction_accuracy":40.09},"site":{"3d_information_understanding_caa":73.13,"counting_and_existence_caa":63.06,"movement_prediction_and_navigation_caa":60.66,"object_localization_and_positioning_caa":57,"spatial_relationship_reasoning_caa":72.25,"multiview_and_crossimage_reasoning_caa":49.92},"blink":{"art_style":85.47,"counting":69.17,"forensic_detection":79.55,"functional_correspondence":60,"iq_test":32.67,"jigsaw":70,"multi_view_reasoning":40.6,"object_localization":61.48,"relative_depth":81.45,"relative_reflectance":32.84,"semantic_correspondence":66.19,"spatial_relation":88.81,"visual_correspondence":94.19,"visual_similarity":87.41},"3dsrbench":{"height_higher":66.09,"location_above":67.77,"location_closer_to_camera":82.74,"location_next_to":72.86,"multi_object_closer_to":64.86,"multi_object_facing":63.87,"multi_object_parallel":54.57,"multi_object_same_direction":45.06,"multi_object_viewpoint_towards_object":22.16,"orientation_in_front_of":74.42,"orientation_on_the_left":40.11,"orientation_viewpoint":33.82},"embspatial":{"mp3d_accuracy":81.35,"ai2thor_accuracy":80.55,"scannet_accuracy":83},"mmsi_video_bench":{"instance_scene_attribute_accuracy":34.94,"instance_instance_spatial_relationship_accuracy":31.58,"instance_scene_spatial_relationship_accuracy":33.77,"scene_scene_spatial_relationship_accuracy":33.33,"camera_instance_spatial_relationship_accuracy":44.3,"camera_scene_spatial_relationship_accuracy":40,"camera_motion_accuracy":45.16,"instance_motion_accuracy":28.89,"interactive_motion_accuracy":34.57,"memoery_update_accuracy":37.25,"multi_view_integration_accuracy":27.14,"planning_accuracy":22.58,"prediction_accuracy":23.17},"omnispatial_(manual_cot)":{"manipulation_accuracy":72.97,"motion_analysis_accuracy":70.52,"traffic_analysis_accuracy":68.67,"localization_accuracy":78.1,"geospatial_strategy_accuracy":69.09,"pattern_recognition_accuracy":41.24,"geometric_reasoning_accuracy":31.61,"egocentric_accuracy":84.31,"allocentric_accuracy":50.37,"hypothetical_accuracy":48.19},"spar_bench":{"depth_prediction_oc":61.53,"depth_prediction_oc_mv":44.62,"depth_prediction_oo":28.15,"depth_prediction_oo_mv":17.42,"distance_prediction_oc":55.11,"distance_prediction_oc_mv":48.88,"distance_prediction_oo":49.12,"distance_prediction_oo_mv":35.49,"position_matching_accuracy":65.14,"camera_motion_infer_accuracy":24.5,"view_change_infer_vci_metric":27.68,"distance_infer_center_oo_accuracy":76.47,"distance_infer_center_oo_mv_accuracy":73.21,"obj_spatial_relation_oc_mv_accuracy":64.5,"obj_spatial_relation_oo_accuracy":62.09,"obj_spatial_relation_oo_mv_accuracy":66.48,"spatial_imagination_oc_accuracy":51.61,"spatial_imagination_oc_mv_accuracy":47.67,"spatial_imagination_oo_accuracy":44.7,"spatial_imagination_oo_mv_accuracy":50.42}}},{"name":"cambrian_s_3b","displayName":"Cambrian-S-3B","link":"https://huggingface.co/nyu-visionx/Cambrian-S-3B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":56.08,"mmsi_bench":27,"mindcube_tiny":38.36,"viewspatial":40.97,"site":30.98,"blink":37.72,"3dsrbench":41.38,"embspatial":63.52,"mmsi_video_bench":23.87,"omnispatial_(manual_cot)":41.88,"spar_bench":33.02,"vsi_debiased":48.76},"subScores":{"vsi_bench":{"object_counting":69.38,"object_abs_distance":38.69,"object_size_estimation":66.33,"room_size_estimation":52.67,"object_rel_distance_accuracy":61.83,"object_rel_direction_accuracy":58.25,"route_planning_accuracy":28.35,"obj_appearance_order_accuracy":73.14},"mmsi_bench":{"pos_cam_cam_accuracy":25.81,"pos_obj_obj_accuracy":28.72,"pos_reg_reg_accuracy":24.69,"pos_cam_obj_accuracy":48.84,"pos_obj_reg_accuracy":24.71,"pos_cam_reg_accuracy":33.73,"attr_meas_accuracy":29.69,"attr_appr_accuracy":22.73,"motion_cam_accuracy":20.27,"motion_obj_accuracy":28.95,"msr_accuracy":18.69},"mindcube_tiny":{"rotation_accuracy":28,"among_accuracy":40,"around_accuracy":42.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":46.98,"camera_perspective_object_view_orientation_accuracy":20.98,"person_perspective_object_view_orientation_accuracy":50.1,"person_perspective_relative_direction_accuracy":39.79,"person_perspective_scene_simulation_relative_direction_accuracy":41.99},"site":{"3d_information_understanding_caa":16.44,"counting_and_existence_caa":47.06,"movement_prediction_and_navigation_caa":24.6,"object_localization_and_positioning_caa":46.18,"spatial_relationship_reasoning_caa":43.99,"multiview_and_crossimage_reasoning_caa":1.43},"blink":{"art_style":32.48,"counting":63.33,"forensic_detection":15.15,"functional_correspondence":20,"iq_test":27.33,"jigsaw":50,"multi_view_reasoning":6.77,"object_localization":50.82,"relative_depth":54.03,"relative_reflectance":31.34,"semantic_correspondence":31.65,"spatial_relation":66.43,"visual_correspondence":34.3,"visual_similarity":46.67},"3dsrbench":{"height_higher":33.48,"location_above":46.24,"location_closer_to_camera":52.8,"location_next_to":61.65,"multi_object_closer_to":53.43,"multi_object_facing":55.78,"multi_object_parallel":43.95,"multi_object_same_direction":50,"multi_object_viewpoint_towards_object":10.5,"orientation_in_front_of":38.95,"orientation_on_the_left":26.65,"orientation_viewpoint":15.16},"embspatial":{"mp3d_accuracy":63.45,"ai2thor_accuracy":60.21,"scannet_accuracy":67},"mmsi_video_bench":{"instance_scene_attribute_accuracy":16.87,"instance_instance_spatial_relationship_accuracy":23.68,"instance_scene_spatial_relationship_accuracy":19.48,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":29.11,"camera_scene_spatial_relationship_accuracy":30,"camera_motion_accuracy":23.66,"instance_motion_accuracy":20,"interactive_motion_accuracy":14.81,"memoery_update_accuracy":23.53,"multi_view_integration_accuracy":24.29,"planning_accuracy":25,"prediction_accuracy":32.93},"omnispatial_(manual_cot)":{"manipulation_accuracy":54.05,"motion_analysis_accuracy":46.24,"traffic_analysis_accuracy":55.29,"localization_accuracy":34.29,"geospatial_strategy_accuracy":40.91,"pattern_recognition_accuracy":25.77,"geometric_reasoning_accuracy":28.39,"egocentric_accuracy":75.49,"allocentric_accuracy":36.7,"hypothetical_accuracy":36.14},"spar_bench":{"depth_prediction_oc":18.39,"depth_prediction_oc_mv":28.16,"depth_prediction_oo":24.01,"depth_prediction_oo_mv":20.56,"distance_prediction_oc":21.04,"distance_prediction_oc_mv":24.52,"distance_prediction_oo":39.15,"distance_prediction_oo_mv":29.87,"position_matching_accuracy":33.08,"camera_motion_infer_accuracy":33,"view_change_infer_vci_metric":18.12,"distance_infer_center_oo_accuracy":53.82,"distance_infer_center_oo_mv_accuracy":54.76,"obj_spatial_relation_oc_mv_accuracy":67.25,"obj_spatial_relation_oo_accuracy":27.75,"obj_spatial_relation_oo_mv_accuracy":42.94,"spatial_imagination_oc_accuracy":29.57,"spatial_imagination_oc_mv_accuracy":34.88,"spatial_imagination_oo_accuracy":21.52,"spatial_imagination_oo_mv_accuracy":38.1},"vsi_debiased":{"object_counting":69.38,"object_abs_distance":38.69,"object_size_estimation":66.33,"room_size_estimation":52.67,"object_rel_distance_accuracy":61.83,"object_rel_direction_accuracy":58.25,"route_planning_accuracy":28.35,"obj_appearance_order_accuracy":73.14}}},{"name":"cambrian_s_7b","displayName":"Cambrian-S-7B","link":"https://huggingface.co/nyu-visionx/Cambrian-S-7B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":62.92,"mmsi_bench":27.1,"mindcube_tiny":37.88,"viewspatial":41.28,"site":36.15,"blink":37.87,"3dsrbench":45.05,"embspatial":72.83,"mmsi_video_bench":25.23,"omnispatial_(manual_cot)":41.88,"spar_bench":37.91,"vsi_debiased":55.35},"subScores":{"vsi_bench":{"object_counting":68.18,"object_abs_distance":45.79,"object_size_estimation":72.47,"room_size_estimation":67.64,"object_rel_distance_accuracy":66.76,"object_rel_direction_accuracy":69.64,"route_planning_accuracy":39.18,"obj_appearance_order_accuracy":73.79},"mmsi_bench":{"pos_cam_cam_accuracy":24.73,"pos_obj_obj_accuracy":26.6,"pos_reg_reg_accuracy":24.69,"pos_cam_obj_accuracy":47.67,"pos_obj_reg_accuracy":22.35,"pos_cam_reg_accuracy":31.33,"attr_meas_accuracy":32.81,"attr_appr_accuracy":24.24,"motion_cam_accuracy":12.16,"motion_obj_accuracy":30.26,"msr_accuracy":24.24},"mindcube_tiny":{"rotation_accuracy":33,"among_accuracy":38.98,"around_accuracy":39.2},"viewspatial":{"camera_perspective_relative_direction_accuracy":50.42,"camera_perspective_object_view_orientation_accuracy":22.69,"person_perspective_object_view_orientation_accuracy":44.98,"person_perspective_relative_direction_accuracy":38.84,"person_perspective_scene_simulation_relative_direction_accuracy":41.9},"site":{"3d_information_understanding_caa":24.11,"counting_and_existence_caa":49.96,"movement_prediction_and_navigation_caa":26.59,"object_localization_and_positioning_caa":50.28,"spatial_relationship_reasoning_caa":51.19,"multiview_and_crossimage_reasoning_caa":8.7},"blink":{"art_style":42.74,"counting":63.33,"forensic_detection":0,"functional_correspondence":20.77,"iq_test":24,"jigsaw":37.33,"multi_view_reasoning":44.36,"object_localization":51.64,"relative_depth":69.35,"relative_reflectance":28.36,"semantic_correspondence":28.78,"spatial_relation":77.62,"visual_correspondence":28.49,"visual_similarity":21.48},"3dsrbench":{"height_higher":43.33,"location_above":46.1,"location_closer_to_camera":58.26,"location_next_to":64.9,"multi_object_closer_to":61.43,"multi_object_facing":48.27,"multi_object_parallel":35.4,"multi_object_same_direction":48.84,"multi_object_viewpoint_towards_object":19.53,"orientation_in_front_of":50.29,"orientation_on_the_left":25.21,"orientation_viewpoint":26.82},"embspatial":{"mp3d_accuracy":71.27,"ai2thor_accuracy":72.88,"scannet_accuracy":74.33},"mmsi_video_bench":{"instance_scene_attribute_accuracy":26.51,"instance_instance_spatial_relationship_accuracy":25,"instance_scene_spatial_relationship_accuracy":23.38,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":20.25,"camera_scene_spatial_relationship_accuracy":23.75,"camera_motion_accuracy":32.26,"instance_motion_accuracy":21.11,"interactive_motion_accuracy":23.46,"memoery_update_accuracy":28.43,"multi_view_integration_accuracy":35.71,"planning_accuracy":17.74,"prediction_accuracy":26.83},"omnispatial_(manual_cot)":{"manipulation_accuracy":63.51,"motion_analysis_accuracy":45.95,"traffic_analysis_accuracy":58.82,"localization_accuracy":33.33,"geospatial_strategy_accuracy":32.73,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":32.26,"egocentric_accuracy":69.61,"allocentric_accuracy":34.57,"hypothetical_accuracy":45.78},"spar_bench":{"depth_prediction_oc":43.06,"depth_prediction_oc_mv":42.72,"depth_prediction_oo":13.68,"depth_prediction_oo_mv":19.92,"distance_prediction_oc":20.97,"distance_prediction_oc_mv":25.89,"distance_prediction_oo":41.93,"distance_prediction_oo_mv":29.7,"position_matching_accuracy":38.17,"camera_motion_infer_accuracy":33.75,"view_change_infer_vci_metric":21.9,"distance_infer_center_oo_accuracy":50.88,"distance_infer_center_oo_mv_accuracy":53.57,"obj_spatial_relation_oc_mv_accuracy":69.25,"obj_spatial_relation_oo_accuracy":42.03,"obj_spatial_relation_oo_mv_accuracy":49.86,"spatial_imagination_oc_accuracy":44.09,"spatial_imagination_oc_mv_accuracy":46.51,"spatial_imagination_oo_accuracy":32.45,"spatial_imagination_oo_mv_accuracy":37.82},"vsi_debiased":{"object_counting":68.18,"object_abs_distance":45.79,"object_size_estimation":72.47,"room_size_estimation":67.64,"object_rel_distance_accuracy":66.76,"object_rel_direction_accuracy":69.64,"route_planning_accuracy":39.18,"obj_appearance_order_accuracy":73.79}}},{"name":"qwen3_vl_8b_instruct","displayName":"Qwen3-VL-8B-Instruct","link":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":55.2924,"vsi_bench_128frames":59.7804,"mmsi_bench":31.1,"mindcube_tiny":29.42,"viewspatial":42.2,"site":45.83,"blink":66.7,"3dsrbench":53.93,"embspatial":77.72,"mmsi_video_bench":28.39,"omnispatial_(manual_cot)":46.97,"spar_bench":39.62,"vsi_debiased":53.07},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":64.5631,"object_abs_distance":46.6307,"object_counting":66.5664,"object_rel_direction_accuracy":46.5919,"object_rel_distance_accuracy":52.9577,"object_size_estimation":73.2844,"room_size_estimation":59.2708,"route_planning_accuracy":32.4742},"vsi_bench_128frames":{"obj_appearance_order_accuracy":73.301,"object_abs_distance":52.2782,"object_counting":67.1327,"object_rel_direction_accuracy":54.1272,"object_rel_distance_accuracy":59.8592,"object_size_estimation":76.149,"room_size_estimation":56.7361,"route_planning_accuracy":38.6598},"mmsi_bench":{"pos_cam_cam_accuracy":27.96,"pos_obj_obj_accuracy":37.23,"pos_reg_reg_accuracy":32.1,"pos_cam_obj_accuracy":31.4,"pos_obj_reg_accuracy":35.29,"pos_cam_reg_accuracy":38.55,"attr_meas_accuracy":37.5,"attr_appr_accuracy":15.15,"motion_cam_accuracy":27.03,"motion_obj_accuracy":28.95,"msr_accuracy":29.8},"mindcube_tiny":{"rotation_accuracy":29.5,"among_accuracy":28.64,"around_accuracy":31.2},"viewspatial":{"camera_perspective_relative_direction_accuracy":54.2,"camera_perspective_object_view_orientation_accuracy":29.72,"person_perspective_object_view_orientation_accuracy":47.29,"person_perspective_relative_direction_accuracy":40.26,"person_perspective_scene_simulation_relative_direction_accuracy":31.13},"site":{"3d_information_understanding_caa":28.52,"counting_and_existence_caa":55.78,"movement_prediction_and_navigation_caa":29.95,"object_localization_and_positioning_caa":60.91,"spatial_relationship_reasoning_caa":67.83,"multiview_and_crossimage_reasoning_caa":22.48},"blink":{"art_style":77.78,"counting":67.5,"forensic_detection":87.88,"functional_correspondence":53.85,"iq_test":12,"jigsaw":67.33,"multi_view_reasoning":54.14,"object_localization":69.67,"relative_depth":88.71,"relative_reflectance":32.09,"semantic_correspondence":59.71,"spatial_relation":87.41,"visual_correspondence":89.53,"visual_similarity":88.15},"3dsrbench":{"height_higher":47.83,"location_above":62.57,"location_closer_to_camera":87.61,"location_next_to":57.82,"multi_object_closer_to":62,"multi_object_facing":65.61,"multi_object_parallel":46.02,"multi_object_same_direction":47.09,"multi_object_viewpoint_towards_object":13.12,"orientation_in_front_of":56.69,"orientation_on_the_left":30.37,"orientation_viewpoint":34.99},"embspatial":{"mp3d_accuracy":79.6,"ai2thor_accuracy":75.06,"scannet_accuracy":78.58},"mmsi_video_bench":{"instance_scene_attribute_accuracy":31.33,"instance_instance_spatial_relationship_accuracy":28.95,"instance_scene_spatial_relationship_accuracy":28.57,"scene_scene_spatial_relationship_accuracy":28.99,"camera_instance_spatial_relationship_accuracy":26.58,"camera_scene_spatial_relationship_accuracy":27.5,"camera_motion_accuracy":33.33,"instance_motion_accuracy":33.33,"interactive_motion_accuracy":30.86,"memoery_update_accuracy":35.29,"multi_view_integration_accuracy":21.43,"planning_accuracy":23.39,"prediction_accuracy":18.29},"omnispatial_(manual_cot)":{"manipulation_accuracy":64.86,"motion_analysis_accuracy":62.14,"traffic_analysis_accuracy":52.94,"localization_accuracy":61.9,"geospatial_strategy_accuracy":55.45,"pattern_recognition_accuracy":22.68,"geometric_reasoning_accuracy":25.81,"egocentric_accuracy":73.53,"allocentric_accuracy":31.38,"hypothetical_accuracy":37.35},"spar_bench":{"depth_prediction_oc":45.17,"depth_prediction_oc_mv":52.16,"depth_prediction_oo":20.24,"depth_prediction_oo_mv":19.57,"distance_prediction_oc":20.05,"distance_prediction_oc_mv":33.59,"distance_prediction_oo":50.25,"distance_prediction_oo_mv":43.5,"position_matching_accuracy":52.16,"camera_motion_infer_accuracy":26,"view_change_infer_vci_metric":16.11,"distance_infer_center_oo_accuracy":71.18,"distance_infer_center_oo_mv_accuracy":67.86,"obj_spatial_relation_oc_mv_accuracy":50.5,"obj_spatial_relation_oo_accuracy":61.26,"obj_spatial_relation_oo_mv_accuracy":38.5,"spatial_imagination_oc_accuracy":29.03,"spatial_imagination_oc_mv_accuracy":31.4,"spatial_imagination_oo_accuracy":33.44,"spatial_imagination_oo_mv_accuracy":30.53},"vsi_debiased":{"object_counting":67.58,"object_abs_distance":47,"object_size_estimation":76.32,"room_size_estimation":61.94,"object_rel_distance_accuracy":58.03,"object_rel_direction_accuracy":50.97,"route_planning_accuracy":35.05,"obj_appearance_order_accuracy":66.34}}},{"name":"vst_3b_sft","displayName":"VST-3B-SFT","link":"https://huggingface.co/rayruiyang/VST-3B-SFT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":51.38,"mmsi_bench":28.8,"mindcube_tiny":35.96,"viewspatial":52.89,"site":35.89,"blink":58.81,"3dsrbench":48.71,"embspatial":68.98,"mmsi_video_bench":24.32,"omnispatial_(manual_cot)":36.46,"spar_bench":37.71,"vsi_debiased":46.48},"subScores":{"vsi_bench":{"object_counting":60.74,"object_abs_distance":37.51,"object_size_estimation":72.73,"room_size_estimation":45.87,"object_rel_distance_accuracy":51.27,"object_rel_direction_accuracy":45.91,"route_planning_accuracy":40.21,"obj_appearance_order_accuracy":56.8},"mmsi_bench":{"pos_cam_cam_accuracy":32.26,"pos_obj_obj_accuracy":31.91,"pos_reg_reg_accuracy":28.4,"pos_cam_obj_accuracy":27.91,"pos_obj_reg_accuracy":23.53,"pos_cam_reg_accuracy":36.14,"attr_meas_accuracy":32.81,"attr_appr_accuracy":34.85,"motion_cam_accuracy":27.03,"motion_obj_accuracy":28.95,"msr_accuracy":22.73},"mindcube_tiny":{"rotation_accuracy":32,"among_accuracy":34.92,"around_accuracy":41.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":46.87,"camera_perspective_object_view_orientation_accuracy":35.44,"person_perspective_object_view_orientation_accuracy":70.28,"person_perspective_relative_direction_accuracy":52.61,"person_perspective_scene_simulation_relative_direction_accuracy":62.81},"site":{"3d_information_understanding_caa":27.7,"counting_and_existence_caa":47.38,"movement_prediction_and_navigation_caa":18.63,"object_localization_and_positioning_caa":35.69,"spatial_relationship_reasoning_caa":57.78,"multiview_and_crossimage_reasoning_caa":16.15},"blink":{"art_style":65.81,"counting":69.17,"forensic_detection":53.03,"functional_correspondence":23.08,"iq_test":33.33,"jigsaw":68,"multi_view_reasoning":51.13,"object_localization":54.1,"relative_depth":86.29,"relative_reflectance":35.82,"semantic_correspondence":30.94,"spatial_relation":74.13,"visual_correspondence":89.53,"visual_similarity":84.44},"3dsrbench":{"height_higher":47.68,"location_above":55.35,"location_closer_to_camera":86.28,"location_next_to":46.31,"multi_object_closer_to":62,"multi_object_facing":57.8,"multi_object_parallel":39.23,"multi_object_same_direction":39.24,"multi_object_viewpoint_towards_object":16.62,"orientation_in_front_of":40.99,"orientation_on_the_left":32.09,"orientation_viewpoint":18.37},"embspatial":{"mp3d_accuracy":71.69,"ai2thor_accuracy":63.28,"scannet_accuracy":72.17},"mmsi_video_bench":{"instance_scene_attribute_accuracy":16.87,"instance_instance_spatial_relationship_accuracy":18.42,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":21.74,"camera_instance_spatial_relationship_accuracy":24.05,"camera_scene_spatial_relationship_accuracy":26.25,"camera_motion_accuracy":25.81,"instance_motion_accuracy":24.44,"interactive_motion_accuracy":20.99,"memoery_update_accuracy":29.41,"multi_view_integration_accuracy":20,"planning_accuracy":28.23,"prediction_accuracy":30.49},"omnispatial_(manual_cot)":{"manipulation_accuracy":56.76,"motion_analysis_accuracy":38.73,"traffic_analysis_accuracy":40,"localization_accuracy":49.52,"geospatial_strategy_accuracy":52.73,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":19.35,"egocentric_accuracy":64.71,"allocentric_accuracy":26.86,"hypothetical_accuracy":19.28},"spar_bench":{"depth_prediction_oc":64.03,"depth_prediction_oc_mv":56.88,"depth_prediction_oo":26.59,"depth_prediction_oo_mv":23.52,"distance_prediction_oc":16.16,"distance_prediction_oc_mv":23.78,"distance_prediction_oo":49.92,"distance_prediction_oo_mv":38.96,"position_matching_accuracy":34.35,"camera_motion_infer_accuracy":26.5,"view_change_infer_vci_metric":13.35,"distance_infer_center_oo_accuracy":80.59,"distance_infer_center_oo_mv_accuracy":74.11,"obj_spatial_relation_oc_mv_accuracy":44,"obj_spatial_relation_oo_accuracy":52.2,"obj_spatial_relation_oo_mv_accuracy":15.79,"spatial_imagination_oc_accuracy":34.68,"spatial_imagination_oc_mv_accuracy":34.59,"spatial_imagination_oo_accuracy":29.14,"spatial_imagination_oo_mv_accuracy":15.13},"vsi_debiased":{"object_counting":60.74,"object_abs_distance":37.51,"object_size_estimation":72.73,"room_size_estimation":45.87,"object_rel_distance_accuracy":51.27,"object_rel_direction_accuracy":45.91,"route_planning_accuracy":40.21,"obj_appearance_order_accuracy":56.8}}},{"name":"vst_7b_sft","displayName":"VST-7B-SFT","link":"https://huggingface.co/rayruiyang/VST-7B-SFT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":55.5,"mmsi_bench":32.5,"mindcube_tiny":39.71,"viewspatial":50.53,"site":39.66,"blink":61.91,"3dsrbench":53.09,"embspatial":73.74,"mmsi_video_bench":24.95,"omnispatial_(manual_cot)":39.53,"spar_bench":46.61,"vsi_debiased":48.75},"subScores":{"vsi_bench":{"object_counting":68.85,"object_abs_distance":37.3,"object_size_estimation":74.49,"room_size_estimation":62.22,"object_rel_distance_accuracy":55.21,"object_rel_direction_accuracy":48.66,"route_planning_accuracy":41.75,"obj_appearance_order_accuracy":55.5},"mmsi_bench":{"pos_cam_cam_accuracy":39.78,"pos_obj_obj_accuracy":36.17,"pos_reg_reg_accuracy":35.8,"pos_cam_obj_accuracy":37.21,"pos_obj_reg_accuracy":29.41,"pos_cam_reg_accuracy":33.73,"attr_meas_accuracy":29.69,"attr_appr_accuracy":46.97,"motion_cam_accuracy":36.49,"motion_obj_accuracy":35.53,"msr_accuracy":18.18},"mindcube_tiny":{"rotation_accuracy":37,"among_accuracy":35.93,"around_accuracy":50.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":52.68,"camera_perspective_object_view_orientation_accuracy":29.62,"person_perspective_object_view_orientation_accuracy":51.91,"person_perspective_relative_direction_accuracy":50.71,"person_perspective_scene_simulation_relative_direction_accuracy":64.52},"site":{"3d_information_understanding_caa":33.09,"counting_and_existence_caa":54.65,"movement_prediction_and_navigation_caa":23.23,"object_localization_and_positioning_caa":37.11,"spatial_relationship_reasoning_caa":63.85,"multiview_and_crossimage_reasoning_caa":13.99},"blink":{"art_style":67.52,"counting":70.83,"forensic_detection":55.3,"functional_correspondence":26.92,"iq_test":23.33,"jigsaw":80,"multi_view_reasoning":63.16,"object_localization":54.1,"relative_depth":91.94,"relative_reflectance":34.33,"semantic_correspondence":33.09,"spatial_relation":81.12,"visual_correspondence":94.19,"visual_similarity":85.93},"3dsrbench":{"height_higher":55.8,"location_above":53.32,"location_closer_to_camera":84.51,"location_next_to":55.46,"multi_object_closer_to":72.86,"multi_object_facing":64.16,"multi_object_parallel":43.66,"multi_object_same_direction":45.64,"multi_object_viewpoint_towards_object":17.2,"orientation_in_front_of":53.78,"orientation_on_the_left":32.66,"orientation_viewpoint":24.2},"embspatial":{"mp3d_accuracy":76.19,"ai2thor_accuracy":71.11,"scannet_accuracy":74},"mmsi_video_bench":{"instance_scene_attribute_accuracy":21.69,"instance_instance_spatial_relationship_accuracy":19.74,"instance_scene_spatial_relationship_accuracy":28.57,"scene_scene_spatial_relationship_accuracy":24.64,"camera_instance_spatial_relationship_accuracy":12.66,"camera_scene_spatial_relationship_accuracy":20,"camera_motion_accuracy":29.03,"instance_motion_accuracy":25.56,"interactive_motion_accuracy":22.22,"memoery_update_accuracy":28.43,"multi_view_integration_accuracy":27.14,"planning_accuracy":32.26,"prediction_accuracy":26.83},"omnispatial_(manual_cot)":{"manipulation_accuracy":55.41,"motion_analysis_accuracy":42.77,"traffic_analysis_accuracy":38.82,"localization_accuracy":54.29,"geospatial_strategy_accuracy":50.91,"pattern_recognition_accuracy":24.74,"geometric_reasoning_accuracy":29.03,"egocentric_accuracy":71.57,"allocentric_accuracy":30.59,"hypothetical_accuracy":16.87},"spar_bench":{"depth_prediction_oc":64.86,"depth_prediction_oc_mv":54.37,"depth_prediction_oo":27.77,"depth_prediction_oo_mv":25.46,"distance_prediction_oc":39.26,"distance_prediction_oc_mv":45.81,"distance_prediction_oo":53.69,"distance_prediction_oo_mv":38.96,"position_matching_accuracy":35.88,"camera_motion_infer_accuracy":31.75,"view_change_infer_vci_metric":16.55,"distance_infer_center_oo_accuracy":86.76,"distance_infer_center_oo_mv_accuracy":80.95,"obj_spatial_relation_oc_mv_accuracy":56.25,"obj_spatial_relation_oo_accuracy":65.38,"obj_spatial_relation_oo_mv_accuracy":49.31,"spatial_imagination_oc_accuracy":41.94,"spatial_imagination_oc_mv_accuracy":45.06,"spatial_imagination_oo_accuracy":30.46,"spatial_imagination_oo_mv_accuracy":41.74},"vsi_debiased":{"object_counting":68.85,"object_abs_distance":37.3,"object_size_estimation":74.49,"room_size_estimation":62.22,"object_rel_distance_accuracy":55.21,"object_rel_direction_accuracy":48.66,"route_planning_accuracy":41.75,"obj_appearance_order_accuracy":55.5}}},{"name":"seed_1.6","displayName":"Seed 1.6","link":"https://seed.bytedance.com/en/seed1_6","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":49.91,"mmsi_bench":38.3,"mindcube_tiny":48.75,"viewspatial":43.86,"site":54.61,"blink":65.91,"3dsrbench":56.93,"embspatial":75.36,"mmsi_video_bench":29.84,"omnispatial_(manual_cot)":50.62,"spar_bench":50.06,"vsi_debiased":48.29},"subScores":{"vsi_bench":{"object_counting":43.54,"object_abs_distance":34.36,"object_size_estimation":66.12,"room_size_estimation":52.81,"object_rel_distance_accuracy":55.07,"object_rel_direction_accuracy":35.74,"route_planning_accuracy":44.33,"obj_appearance_order_accuracy":67.96},"mmsi_bench":{"pos_cam_cam_accuracy":36.56,"pos_obj_obj_accuracy":36.17,"pos_reg_reg_accuracy":32.1,"pos_cam_obj_accuracy":32.56,"pos_obj_reg_accuracy":42.35,"pos_cam_reg_accuracy":46.94,"attr_meas_accuracy":48.44,"attr_appr_accuracy":33,"motion_cam_accuracy":31.08,"motion_obj_accuracy":42.11,"msr_accuracy":40.4},"mindcube_tiny":{"rotation_accuracy":89,"among_accuracy":36.44,"around_accuracy":45.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":55.78,"camera_perspective_object_view_orientation_accuracy":26.91,"person_perspective_object_view_orientation_accuracy":54.82,"person_perspective_relative_direction_accuracy":48.46,"person_perspective_scene_simulation_relative_direction_accuracy":26.61},"site":{"counting_and_existence_caa":61.96,"object_localization_and_positioning_caa":66.45,"3d_information_understanding_caa":60.41,"multiview_and_crossimage_reasoning_caa":37.13,"spatial_relationship_reasoning_caa":70.59,"movement_prediction_and_navigation_caa":32.44},"blink":{"art_style":80.34,"counting":74.17,"forensic_detection":62.88,"functional_correspondence":53.08,"iq_test":28.67,"jigsaw":59.33,"multi_view_reasoning":55.64,"object_localization":64.75,"relative_depth":85.48,"relative_reflectance":32.09,"semantic_correspondence":64.75,"spatial_relation":86.71,"visual_correspondence":90.7,"visual_similarity":84.44},"3dsrbench":{"height_higher":67.68,"location_above":64.31,"location_closer_to_camera":74.93,"location_next_to":67.85,"multi_object_closer_to":67.14,"multi_object_facing":64.45,"multi_object_parallel":56.64,"multi_object_same_direction":48.84,"multi_object_viewpoint_towards_object":17.49,"orientation_in_front_of":61.92,"orientation_on_the_left":32.66,"orientation_viewpoint":23.62},"embspatial":{"mp3d_accuracy":74.35,"ai2thor_accuracy":75.06,"scannet_accuracy":76.67},"omnispatial_(manual_cot)":{"manipulation_accuracy":67.57,"motion_analysis_accuracy":59.54,"traffic_analysis_accuracy":54.12,"localization_accuracy":75.24,"geospatial_strategy_accuracy":60.91,"pattern_recognition_accuracy":30.93,"geometric_reasoning_accuracy":27.74,"egocentric_accuracy":77.45,"allocentric_accuracy":32.98,"hypothetical_accuracy":38.55}}},{"name":"sensenova_si_1.1_internvl3_8b","displayName":"SenseNova-SI-1.1-InternVL3-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":68.78,"mmsi_bench":43.3,"mindcube_tiny":85.67,"viewspatial":54.67,"site":47.74,"blink":63.91,"3dsrbench":55.54,"embspatial":72.01,"mmsi_video_bench":23.78,"omnispatial_(manual_cot)":33.01,"spar_bench":45.78,"vsi_debiased":62.89},"subScores":{"vsi_bench":{"object_counting":72.02,"object_abs_distance":53.5,"object_size_estimation":76.77,"room_size_estimation":72.78,"object_rel_distance_accuracy":69.58,"object_rel_direction_accuracy":80.75,"route_planning_accuracy":48.45,"obj_appearance_order_accuracy":76.38},"mmsi_bench":{"pos_cam_cam_accuracy":50.54,"pos_obj_obj_accuracy":47.87,"pos_reg_reg_accuracy":41.98,"pos_cam_obj_accuracy":62.79,"pos_obj_reg_accuracy":44.71,"pos_cam_reg_accuracy":69.88,"attr_meas_accuracy":40.62,"attr_appr_accuracy":40.91,"motion_cam_accuracy":32.43,"motion_obj_accuracy":32.89,"msr_accuracy":27.78},"mindcube_tiny":{"rotation_accuracy":82,"among_accuracy":84.92,"around_accuracy":90.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":66.27,"camera_perspective_object_view_orientation_accuracy":43.17,"person_perspective_object_view_orientation_accuracy":38.35,"person_perspective_relative_direction_accuracy":43.11,"person_perspective_scene_simulation_relative_direction_accuracy":69.95},"site":{"3d_information_understanding_caa":40.6,"counting_and_existence_caa":56.19,"movement_prediction_and_navigation_caa":40.53,"object_localization_and_positioning_caa":49.15,"spatial_relationship_reasoning_caa":57.6,"multiview_and_crossimage_reasoning_caa":35.12},"blink":{"art_style":68.38,"counting":76.67,"forensic_detection":32.58,"functional_correspondence":33.85,"iq_test":21.33,"jigsaw":80,"multi_view_reasoning":90.23,"object_localization":54.92,"relative_depth":93.55,"relative_reflectance":32.84,"semantic_correspondence":46.04,"spatial_relation":86.01,"visual_correspondence":95.93,"visual_similarity":77.78},"3dsrbench":{"height_higher":49.13,"location_above":51.45,"location_closer_to_camera":83.78,"location_next_to":59.29,"multi_object_closer_to":75.71,"multi_object_facing":59.25,"multi_object_parallel":46.9,"multi_object_same_direction":53.2,"multi_object_viewpoint_towards_object":16.91,"orientation_in_front_of":60.17,"orientation_on_the_left":60.46,"orientation_viewpoint":32.65},"embspatial":{"mp3d_accuracy":71.02,"ai2thor_accuracy":70.54,"scannet_accuracy":75.08},"mmsi_video_bench":{"instance_scene_attribute_accuracy":16.87,"instance_instance_spatial_relationship_accuracy":35.53,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":23.19,"camera_instance_spatial_relationship_accuracy":16.46,"camera_scene_spatial_relationship_accuracy":23.75,"camera_motion_accuracy":33.33,"instance_motion_accuracy":23.33,"interactive_motion_accuracy":22.22,"memoery_update_accuracy":29.41,"multi_view_integration_accuracy":17.14,"planning_accuracy":20.97,"prediction_accuracy":20.73},"omnispatial_(manual_cot)":{"manipulation_accuracy":44.59,"motion_analysis_accuracy":39.31,"traffic_analysis_accuracy":40,"localization_accuracy":40,"geospatial_strategy_accuracy":46.36,"pattern_recognition_accuracy":18.56,"geometric_reasoning_accuracy":34.84,"egocentric_accuracy":61.76,"allocentric_accuracy":17.02,"hypothetical_accuracy":13.25},"spar_bench":{"depth_prediction_oc":69.67,"depth_prediction_oc_mv":55.5,"depth_prediction_oo":13.68,"depth_prediction_oo_mv":22.85,"distance_prediction_oc":63.69,"distance_prediction_oc_mv":59.64,"distance_prediction_oo":50.58,"distance_prediction_oo_mv":35.52,"position_matching_accuracy":46.31,"camera_motion_infer_accuracy":40.75,"view_change_infer_vci_metric":14.34,"distance_infer_center_oo_accuracy":60.29,"distance_infer_center_oo_mv_accuracy":56.85,"obj_spatial_relation_oc_mv_accuracy":56,"obj_spatial_relation_oo_accuracy":67.86,"obj_spatial_relation_oo_mv_accuracy":39.34,"spatial_imagination_oc_accuracy":53.23,"spatial_imagination_oc_mv_accuracy":47.97,"spatial_imagination_oo_accuracy":33.44,"spatial_imagination_oo_mv_accuracy":28.01},"vsi_debiased":{"object_counting":72.02,"object_abs_distance":53.5,"object_size_estimation":76.77,"room_size_estimation":72.78,"object_rel_distance_accuracy":69.58,"object_rel_direction_accuracy":80.75,"route_planning_accuracy":48.45,"obj_appearance_order_accuracy":76.38}}},{"name":"sensenova_si_1.1_internvl3_2b","displayName":"SenseNova-SI-1.1-InternVL3-2B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-InternVL3-2B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":63.72,"mmsi_bench":34.2,"mindcube_tiny":41.83,"viewspatial":52.66,"site":36.78,"blink":52.39,"3dsrbench":50.48,"embspatial":62.75,"mmsi_video_bench":20.43,"omnispatial_(manual_cot)":26.35,"spar_bench":37.96,"vsi_debiased":55.96},"subScores":{"vsi_bench":{"object_counting":70.14,"object_abs_distance":47.19,"object_size_estimation":74.46,"room_size_estimation":67.05,"object_rel_distance_accuracy":60.99,"object_rel_direction_accuracy":73.11,"route_planning_accuracy":41.24,"obj_appearance_order_accuracy":75.57},"mmsi_bench":{"pos_cam_cam_accuracy":39.78,"pos_obj_obj_accuracy":45.74,"pos_reg_reg_accuracy":33.33,"pos_cam_obj_accuracy":46.51,"pos_obj_reg_accuracy":30.59,"pos_cam_reg_accuracy":39.76,"attr_meas_accuracy":31.25,"attr_appr_accuracy":30.3,"motion_cam_accuracy":29.73,"motion_obj_accuracy":32.89,"msr_accuracy":24.75},"mindcube_tiny":{"rotation_accuracy":30.5,"among_accuracy":46.44,"around_accuracy":40},"viewspatial":{"camera_perspective_relative_direction_accuracy":65.71,"camera_perspective_object_view_orientation_accuracy":19.48,"person_perspective_object_view_orientation_accuracy":70.18,"person_perspective_relative_direction_accuracy":39.43,"person_perspective_scene_simulation_relative_direction_accuracy":55.93},"site":{"3d_information_understanding_caa":23.13,"counting_and_existence_caa":51.02,"movement_prediction_and_navigation_caa":26.84,"object_localization_and_positioning_caa":45.75,"spatial_relationship_reasoning_caa":48.93,"multiview_and_crossimage_reasoning_caa":16.07},"blink":{"art_style":61.54,"counting":65.83,"forensic_detection":12.88,"functional_correspondence":35.38,"iq_test":21.33,"jigsaw":63.33,"multi_view_reasoning":6.02,"object_localization":58.2,"relative_depth":80.65,"relative_reflectance":35.07,"semantic_correspondence":35.97,"spatial_relation":74.13,"visual_correspondence":93.02,"visual_similarity":83.7},"3dsrbench":{"height_higher":50,"location_above":51.59,"location_closer_to_camera":66.81,"location_next_to":64.9,"multi_object_closer_to":66.86,"multi_object_facing":66.18,"multi_object_parallel":48.97,"multi_object_same_direction":50,"multi_object_viewpoint_towards_object":21.28,"orientation_in_front_of":45.93,"orientation_on_the_left":28.94,"orientation_viewpoint":27.7},"embspatial":{"mp3d_accuracy":64.2,"ai2thor_accuracy":56.66,"scannet_accuracy":67.58},"mmsi_video_bench":{"instance_scene_attribute_accuracy":14.46,"instance_instance_spatial_relationship_accuracy":23.68,"instance_scene_spatial_relationship_accuracy":20.78,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":11.39,"camera_scene_spatial_relationship_accuracy":17.5,"camera_motion_accuracy":24.73,"instance_motion_accuracy":23.33,"interactive_motion_accuracy":18.52,"memoery_update_accuracy":22.55,"multi_view_integration_accuracy":14.29,"planning_accuracy":22.58,"prediction_accuracy":21.95},"omnispatial_(manual_cot)":{"manipulation_accuracy":37.84,"motion_analysis_accuracy":41.04,"traffic_analysis_accuracy":20,"localization_accuracy":40.95,"geospatial_strategy_accuracy":25.45,"pattern_recognition_accuracy":18.56,"geometric_reasoning_accuracy":29.03,"egocentric_accuracy":34.31,"allocentric_accuracy":12.5,"hypothetical_accuracy":1.2},"spar_bench":{"depth_prediction_oc":64.89,"depth_prediction_oc_mv":47.56,"depth_prediction_oo":12.53,"depth_prediction_oo_mv":20.38,"distance_prediction_oc":40.92,"distance_prediction_oc_mv":39.92,"distance_prediction_oo":49.83,"distance_prediction_oo_mv":39.23,"position_matching_accuracy":43.51,"camera_motion_infer_accuracy":24.5,"view_change_infer_vci_metric":11.89,"distance_infer_center_oo_accuracy":60.29,"distance_infer_center_oo_mv_accuracy":55.36,"obj_spatial_relation_oc_mv_accuracy":48.25,"obj_spatial_relation_oo_accuracy":57.42,"obj_spatial_relation_oo_mv_accuracy":20.22,"spatial_imagination_oc_accuracy":35.48,"spatial_imagination_oc_mv_accuracy":36.63,"spatial_imagination_oo_accuracy":26.82,"spatial_imagination_oo_mv_accuracy":23.53},"vsi_debiased":{"object_counting":70.14,"object_abs_distance":47.19,"object_size_estimation":74.46,"room_size_estimation":67.05,"object_rel_distance_accuracy":60.99,"object_rel_direction_accuracy":73.11,"route_planning_accuracy":41.24,"obj_appearance_order_accuracy":75.57}}},{"name":"sensenova_si_1.1_bagel_7b_mot","displayName":"SenseNova-SI-1.1-BAGEL-7B-MoT","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-BAGEL-7B-MoT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":41.54,"mmsi_bench":34.5,"mindcube_tiny":46.83,"viewspatial":46.88,"site":42.04,"blink":65.39,"3dsrbench":42.37,"embspatial":68.98,"mmsi_video_bench":23.78,"omnispatial_(manual_cot)":43.97,"spar_bench":44.68,"vsi_debiased":34.98},"subScores":{"vsi_bench":{"object_counting":42.21,"object_abs_distance":33.47,"object_size_estimation":57.19,"room_size_estimation":22.67,"object_rel_distance_accuracy":44.93,"object_rel_direction_accuracy":46.37,"route_planning_accuracy":33.51,"obj_appearance_order_accuracy":51.94},"mmsi_bench":{"pos_cam_cam_accuracy":48.39,"pos_obj_obj_accuracy":34.04,"pos_reg_reg_accuracy":23.46,"pos_cam_obj_accuracy":46.51,"pos_obj_reg_accuracy":34.12,"pos_cam_reg_accuracy":40.96,"attr_meas_accuracy":34.38,"attr_appr_accuracy":33.33,"motion_cam_accuracy":32.43,"motion_obj_accuracy":32.89,"msr_accuracy":26.77},"mindcube_tiny":{"rotation_accuracy":33,"among_accuracy":50.68,"around_accuracy":48.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":54.71,"camera_perspective_object_view_orientation_accuracy":33.53,"person_perspective_object_view_orientation_accuracy":45.88,"person_perspective_relative_direction_accuracy":43.94,"person_perspective_scene_simulation_relative_direction_accuracy":49.5},"site":{"3d_information_understanding_caa":30.64,"counting_and_existence_caa":47.38,"movement_prediction_and_navigation_caa":17.39,"object_localization_and_positioning_caa":62.89,"spatial_relationship_reasoning_caa":59.25,"multiview_and_crossimage_reasoning_caa":27.76},"blink":{"art_style":81.2,"counting":71.67,"forensic_detection":33.33,"functional_correspondence":49.23,"iq_test":28.67,"jigsaw":77.33,"multi_view_reasoning":44.36,"object_localization":77.05,"relative_depth":87.1,"relative_reflectance":33.58,"semantic_correspondence":66.91,"spatial_relation":76.22,"visual_correspondence":94.77,"visual_similarity":91.85},"3dsrbench":{"height_higher":33.48,"location_above":47.4,"location_closer_to_camera":67.7,"location_next_to":47.79,"multi_object_closer_to":43.43,"multi_object_facing":53.47,"multi_object_parallel":43.36,"multi_object_same_direction":46.51,"multi_object_viewpoint_towards_object":2.92,"orientation_in_front_of":47.67,"orientation_on_the_left":28.94,"orientation_viewpoint":23.62},"embspatial":{"mp3d_accuracy":68.19,"ai2thor_accuracy":63.84,"scannet_accuracy":75.08},"mmsi_video_bench":{"instance_scene_attribute_accuracy":13.25,"instance_instance_spatial_relationship_accuracy":15.79,"instance_scene_spatial_relationship_accuracy":25.97,"scene_scene_spatial_relationship_accuracy":23.19,"camera_instance_spatial_relationship_accuracy":31.65,"camera_scene_spatial_relationship_accuracy":25,"camera_motion_accuracy":22.58,"instance_motion_accuracy":23.33,"interactive_motion_accuracy":25.93,"memoery_update_accuracy":32.35,"multi_view_integration_accuracy":20,"planning_accuracy":29.03,"prediction_accuracy":15.85},"omnispatial_(manual_cot)":{"manipulation_accuracy":54.05,"motion_analysis_accuracy":52.02,"traffic_analysis_accuracy":45.88,"localization_accuracy":49.52,"geospatial_strategy_accuracy":40,"pattern_recognition_accuracy":41.24,"geometric_reasoning_accuracy":25.81,"egocentric_accuracy":72.55,"allocentric_accuracy":35.11,"hypothetical_accuracy":39.76},"spar_bench":{"depth_prediction_oc":65.33,"depth_prediction_oc_mv":55.81,"depth_prediction_oo":15.91,"depth_prediction_oo_mv":19.81,"distance_prediction_oc":62.06,"distance_prediction_oc_mv":58.22,"distance_prediction_oo":30.8,"distance_prediction_oo_mv":34.14,"position_matching_accuracy":59.03,"camera_motion_infer_accuracy":31.25,"view_change_infer_vci_metric":15.41,"distance_infer_center_oo_accuracy":64.12,"distance_infer_center_oo_mv_accuracy":60.42,"obj_spatial_relation_oc_mv_accuracy":53.25,"obj_spatial_relation_oo_accuracy":69.51,"obj_spatial_relation_oo_mv_accuracy":41.55,"spatial_imagination_oc_accuracy":36.56,"spatial_imagination_oc_mv_accuracy":38.66,"spatial_imagination_oo_accuracy":38.08,"spatial_imagination_oo_mv_accuracy":43.7},"vsi_debiased":{"object_counting":42.21,"object_abs_distance":33.47,"object_size_estimation":57.19,"room_size_estimation":22.67,"object_rel_distance_accuracy":44.93,"object_rel_direction_accuracy":46.37,"route_planning_accuracy":33.51,"obj_appearance_order_accuracy":51.94}}},{"name":"sensenova_si_1.1_qwen3_vl_8b","displayName":"SenseNova-SI-1.1-Qwen3-VL-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen3-VL-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":64.8,"mmsi_bench":38.1,"mindcube_tiny":73.8,"viewspatial":51.2,"site":49.6,"blink":61.86,"3dsrbench":53.19,"embspatial":72.5,"mmsi_video_bench":25.5,"omnispatial_(manual_cot)":43.05,"spar_bench":40.8,"vsi_debiased":59.42},"subScores":{"vsi_bench":{"object_counting":71.43,"object_abs_distance":48.66,"object_size_estimation":75.98,"room_size_estimation":69.55,"object_rel_distance_accuracy":65.49,"object_rel_direction_accuracy":72.2,"route_planning_accuracy":43.81,"obj_appearance_order_accuracy":71.52},"mmsi_bench":{"pos_cam_cam_accuracy":44.09,"pos_obj_obj_accuracy":38.3,"pos_reg_reg_accuracy":33.33,"pos_cam_obj_accuracy":65.12,"pos_obj_reg_accuracy":38.82,"pos_cam_reg_accuracy":59.04,"attr_meas_accuracy":48.44,"attr_appr_accuracy":24.24,"motion_cam_accuracy":29.73,"motion_obj_accuracy":34.21,"msr_accuracy":22.22},"mindcube_tiny":{"rotation_accuracy":79.5,"among_accuracy":73.22,"around_accuracy":70.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":60.29,"camera_perspective_object_view_orientation_accuracy":21.99,"person_perspective_object_view_orientation_accuracy":67.77,"person_perspective_relative_direction_accuracy":41.45,"person_perspective_scene_simulation_relative_direction_accuracy":55.57},"site":{"3d_information_understanding_caa":39.13,"counting_and_existence_caa":53.12,"movement_prediction_and_navigation_caa":24.85,"object_localization_and_positioning_caa":56.09,"spatial_relationship_reasoning_caa":64.89,"multiview_and_crossimage_reasoning_caa":40.32},"blink":{"art_style":74.36,"counting":61.67,"forensic_detection":69.7,"functional_correspondence":50.77,"iq_test":13.33,"jigsaw":64,"multi_view_reasoning":32.33,"object_localization":65.57,"relative_depth":88.71,"relative_reflectance":30.6,"semantic_correspondence":52.52,"spatial_relation":79.72,"visual_correspondence":93.6,"visual_similarity":88.15},"3dsrbench":{"height_higher":52.17,"location_above":55.92,"location_closer_to_camera":84.96,"location_next_to":58.41,"multi_object_closer_to":66.57,"multi_object_facing":61.85,"multi_object_parallel":41,"multi_object_same_direction":49.13,"multi_object_viewpoint_towards_object":20.7,"orientation_in_front_of":49.71,"orientation_on_the_left":34.1,"orientation_viewpoint":30.9},"embspatial":{"mp3d_accuracy":75.85,"ai2thor_accuracy":66.42,"scannet_accuracy":75.42},"mmsi_video_bench":{"instance_scene_attribute_accuracy":16.87,"instance_instance_spatial_relationship_accuracy":27.63,"instance_scene_spatial_relationship_accuracy":28.57,"scene_scene_spatial_relationship_accuracy":18.84,"camera_instance_spatial_relationship_accuracy":25.32,"camera_scene_spatial_relationship_accuracy":26.25,"camera_motion_accuracy":33.33,"instance_motion_accuracy":26.67,"interactive_motion_accuracy":28.4,"memoery_update_accuracy":26.47,"multi_view_integration_accuracy":20,"planning_accuracy":25.81,"prediction_accuracy":24.39},"omnispatial_(manual_cot)":{"manipulation_accuracy":56.76,"motion_analysis_accuracy":56.36,"traffic_analysis_accuracy":51.76,"localization_accuracy":60,"geospatial_strategy_accuracy":49.09,"pattern_recognition_accuracy":22.68,"geometric_reasoning_accuracy":27.1,"egocentric_accuracy":65.69,"allocentric_accuracy":26.6,"hypothetical_accuracy":37.35},"spar_bench":{"depth_prediction_oc":39.06,"depth_prediction_oc_mv":45.56,"depth_prediction_oo":21.45,"depth_prediction_oo_mv":20.89,"distance_prediction_oc":11.68,"distance_prediction_oc_mv":26.63,"distance_prediction_oo":44.57,"distance_prediction_oo_mv":39.23,"position_matching_accuracy":45.29,"camera_motion_infer_accuracy":37,"view_change_infer_vci_metric":14.22,"distance_infer_center_oo_accuracy":76.18,"distance_infer_center_oo_mv_accuracy":75.3,"obj_spatial_relation_oc_mv_accuracy":61.5,"obj_spatial_relation_oo_accuracy":63.74,"obj_spatial_relation_oo_mv_accuracy":44.32,"spatial_imagination_oc_accuracy":40.05,"spatial_imagination_oc_mv_accuracy":41.57,"spatial_imagination_oo_accuracy":33.77,"spatial_imagination_oo_mv_accuracy":33.89},"vsi_debiased":{"object_counting":71.43,"object_abs_distance":48.66,"object_size_estimation":75.98,"room_size_estimation":69.55,"object_rel_distance_accuracy":65.49,"object_rel_direction_accuracy":72.2,"route_planning_accuracy":43.81,"obj_appearance_order_accuracy":71.52}}},{"name":"vlm_3r_llava_qwen2_lora","displayName":"vlm-3r-llava-qwen2-lora","link":"https://huggingface.co/Journey9ni/vlm-3r-llava-qwen2-lora","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":60.7,"mmsi_bench":27.9,"mindcube_tiny":40,"viewspatial":40.55,"site":31.31,"blink":52.29,"3dsrbench":51.52,"embspatial":68.19,"mmsi_video_bench":27.76,"omnispatial_(manual_cot)":43.31,"spar_bench":42.35,"vsi_debiased":55.46}},{"name":"internvl3_5_8b","displayName":"InternVL3_5-8B","link":"https://huggingface.co/OpenGVLab/InternVL3_5-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":56.06,"mmsi_bench":29,"mindcube_tiny":40.19,"viewspatial":39.99,"site":43.79,"blink":58.23,"3dsrbench":49.2,"embspatial":75.66,"mmsi_video_bench":28.03,"omnispatial_(manual_cot)":47.36,"spar_bench":38.19,"vsi_debiased":50.47},"subScores":{"vsi_bench":{"object_counting":68.58,"object_abs_distance":42.21,"object_size_estimation":68.1,"room_size_estimation":65.21,"object_rel_distance_accuracy":55.49,"object_rel_direction_accuracy":48.19,"route_planning_accuracy":39.18,"obj_appearance_order_accuracy":61.49},"mmsi_bench":{"pos_cam_cam_accuracy":29.03,"pos_obj_obj_accuracy":26.6,"pos_reg_reg_accuracy":29.63,"pos_cam_obj_accuracy":24.42,"pos_obj_reg_accuracy":31.76,"pos_cam_reg_accuracy":25.3,"attr_meas_accuracy":29.69,"attr_appr_accuracy":25.76,"motion_cam_accuracy":14.86,"motion_obj_accuracy":34.21,"msr_accuracy":36.36},"mindcube_tiny":{"rotation_accuracy":34.5,"among_accuracy":38.19,"around_accuracy":44.36},"viewspatial":{"camera_perspective_relative_direction_accuracy":49.75,"camera_perspective_object_view_orientation_accuracy":24.7,"person_perspective_object_view_orientation_accuracy":50.3,"person_perspective_relative_direction_accuracy":34.56,"person_perspective_scene_simulation_relative_direction_accuracy":32.94},"site":{"3d_information_understanding_caa":42.55,"counting_and_existence_caa":59.1,"movement_prediction_and_navigation_caa":33.19,"object_localization_and_positioning_caa":56.52,"spatial_relationship_reasoning_caa":61.25,"multiview_and_crossimage_reasoning_caa":8.44},"blink":{"art_style":71.79,"counting":68.33,"forensic_detection":45.45,"functional_correspondence":29.23,"iq_test":22,"jigsaw":68,"multi_view_reasoning":55.64,"object_localization":64.75,"relative_depth":79.03,"relative_reflectance":30.6,"semantic_correspondence":33.09,"spatial_relation":89.51,"visual_correspondence":72.09,"visual_similarity":87.41},"3dsrbench":{"height_higher":50.14,"location_above":54.34,"location_closer_to_camera":74.78,"location_next_to":56.34,"multi_object_closer_to":57.14,"multi_object_facing":62.14,"multi_object_parallel":48.38,"multi_object_same_direction":32.85,"multi_object_viewpoint_towards_object":14.58,"orientation_in_front_of":46.51,"orientation_on_the_left":32.95,"orientation_viewpoint":29.15},"embspatial":{"mp3d_accuracy":74.77,"ai2thor_accuracy":73.37,"scannet_accuracy":78.92},"mmsi_video_bench":{"instance_scene_attribute_accuracy":33.73,"instance_instance_spatial_relationship_accuracy":32.89,"instance_scene_spatial_relationship_accuracy":22.08,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":22.78,"camera_scene_spatial_relationship_accuracy":23.75,"camera_motion_accuracy":32.26,"instance_motion_accuracy":30,"interactive_motion_accuracy":37.04,"memoery_update_accuracy":28.43,"multi_view_integration_accuracy":22.86,"planning_accuracy":25,"prediction_accuracy":25.61},"omnispatial_(manual_cot)":{"manipulation_accuracy":54.05,"motion_analysis_accuracy":63.29,"traffic_analysis_accuracy":43.53,"localization_accuracy":56.19,"geospatial_strategy_accuracy":57.27,"pattern_recognition_accuracy":26.8,"geometric_reasoning_accuracy":31.61,"egocentric_accuracy":73.53,"allocentric_accuracy":32.18,"hypothetical_accuracy":44.58},"spar_bench":{"depth_prediction_oc":36.89,"depth_prediction_oc_mv":36.78,"depth_prediction_oo":18.06,"depth_prediction_oo_mv":21.85,"distance_prediction_oc":39.49,"distance_prediction_oc_mv":40.38,"distance_prediction_oo":41.24,"distance_prediction_oo_mv":38.89,"position_matching_accuracy":59.8,"camera_motion_infer_accuracy":30.5,"view_change_infer_vci_metric":14.89,"distance_infer_center_oo_accuracy":67.65,"distance_infer_center_oo_mv_accuracy":64.29,"obj_spatial_relation_oc_mv_accuracy":54.25,"obj_spatial_relation_oo_accuracy":41.48,"obj_spatial_relation_oo_mv_accuracy":31.58,"spatial_imagination_oc_accuracy":30.91,"spatial_imagination_oc_mv_accuracy":36.63,"spatial_imagination_oo_accuracy":26.49,"spatial_imagination_oo_mv_accuracy":31.65},"vsi_debiased":{"object_counting":68.58,"object_abs_distance":42.21,"object_size_estimation":68.1,"room_size_estimation":65.21,"object_rel_distance_accuracy":55.49,"object_rel_direction_accuracy":48.19,"route_planning_accuracy":39.18,"obj_appearance_order_accuracy":61.49}}},{"name":"sensenova_si_1.1_qwen2.5_vl_3b","displayName":"SenseNova-SI-1.1-Qwen2.5-VL-3B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-3B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":54.9,"mmsi_bench":30.8,"mindcube_tiny":52.6,"viewspatial":43.5,"site":37.8,"blink":45.61,"3dsrbench":45.01,"embspatial":55.25,"mmsi_video_bench":25.14,"omnispatial_(manual_cot)":32.49,"spar_bench":30.75,"vsi_debiased":47.77},"subScores":{"vsi_bench":{"object_counting":63.49,"object_abs_distance":41.47,"object_size_estimation":69.65,"room_size_estimation":57.47,"object_rel_distance_accuracy":53.1,"object_rel_direction_accuracy":46.27,"route_planning_accuracy":38.66,"obj_appearance_order_accuracy":69.42},"mmsi_bench":{"pos_cam_cam_accuracy":39.78,"pos_obj_obj_accuracy":35.11,"pos_reg_reg_accuracy":34.57,"pos_cam_obj_accuracy":37.21,"pos_obj_reg_accuracy":32.94,"pos_cam_reg_accuracy":36.14,"attr_meas_accuracy":32.81,"attr_appr_accuracy":27.27,"motion_cam_accuracy":12.16,"motion_obj_accuracy":34.21,"msr_accuracy":23.23},"mindcube_tiny":{"rotation_accuracy":35,"among_accuracy":52.2,"around_accuracy":67.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":45.06,"camera_perspective_object_view_orientation_accuracy":28.31,"person_perspective_object_view_orientation_accuracy":59.34,"person_perspective_relative_direction_accuracy":40.14,"person_perspective_scene_simulation_relative_direction_accuracy":42.99},"site":{"3d_information_understanding_caa":26.72,"counting_and_existence_caa":50.77,"movement_prediction_and_navigation_caa":24.23,"object_localization_and_positioning_caa":36.97,"spatial_relationship_reasoning_caa":55,"multiview_and_crossimage_reasoning_caa":11.39},"blink":{"art_style":54.7,"counting":61.67,"forensic_detection":21.97,"functional_correspondence":25.38,"iq_test":24,"jigsaw":48.67,"multi_view_reasoning":51.88,"object_localization":56.56,"relative_depth":61.29,"relative_reflectance":38.81,"semantic_correspondence":28.06,"spatial_relation":83.92,"visual_correspondence":33.72,"visual_similarity":55.56},"3dsrbench":{"height_higher":42.9,"location_above":57.95,"location_closer_to_camera":67.11,"location_next_to":48.97,"multi_object_closer_to":49.14,"multi_object_facing":59.25,"multi_object_parallel":40.71,"multi_object_same_direction":51.74,"multi_object_viewpoint_towards_object":8.45,"orientation_in_front_of":42.73,"orientation_on_the_left":30.66,"orientation_viewpoint":7.87},"embspatial":{"mp3d_accuracy":58.53,"ai2thor_accuracy":51.01,"scannet_accuracy":56.33},"mmsi_video_bench":{"instance_scene_attribute_accuracy":15.66,"instance_instance_spatial_relationship_accuracy":23.68,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":24.64,"camera_instance_spatial_relationship_accuracy":22.78,"camera_scene_spatial_relationship_accuracy":25,"camera_motion_accuracy":21.51,"instance_motion_accuracy":26.67,"interactive_motion_accuracy":29.63,"memoery_update_accuracy":27.45,"multi_view_integration_accuracy":30,"planning_accuracy":28.23,"prediction_accuracy":25.61},"omnispatial_(manual_cot)":{"manipulation_accuracy":54.05,"motion_analysis_accuracy":46.24,"traffic_analysis_accuracy":37.65,"localization_accuracy":36.19,"geospatial_strategy_accuracy":30.91,"pattern_recognition_accuracy":23.71,"geometric_reasoning_accuracy":30.97,"egocentric_accuracy":43.14,"allocentric_accuracy":19.15,"hypothetical_accuracy":8.43},"spar_bench":{"depth_prediction_oc":39.78,"depth_prediction_oc_mv":32.09,"depth_prediction_oo":23.66,"depth_prediction_oo_mv":24.38,"distance_prediction_oc":17.79,"distance_prediction_oc_mv":25.78,"distance_prediction_oo":41.63,"distance_prediction_oo_mv":30.57,"position_matching_accuracy":32.57,"camera_motion_infer_accuracy":31.75,"view_change_infer_vci_metric":15.1,"distance_infer_center_oo_accuracy":56.47,"distance_infer_center_oo_mv_accuracy":57.44,"obj_spatial_relation_oc_mv_accuracy":42.25,"obj_spatial_relation_oo_accuracy":40.66,"obj_spatial_relation_oo_mv_accuracy":14.4,"spatial_imagination_oc_accuracy":23.66,"spatial_imagination_oc_mv_accuracy":23.84,"spatial_imagination_oo_accuracy":23.18,"spatial_imagination_oo_mv_accuracy":17.93},"vsi_debiased":{"object_counting":63.49,"object_abs_distance":41.47,"object_size_estimation":69.65,"room_size_estimation":57.47,"object_rel_distance_accuracy":53.1,"object_rel_direction_accuracy":46.27,"route_planning_accuracy":38.66,"obj_appearance_order_accuracy":69.42}}},{"name":"sensenova_si_1.1_qwen2.5_vl_7b","displayName":"SenseNova-SI-1.1-Qwen2.5-VL-7B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.1-Qwen2.5-VL-7B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":58.1,"mmsi_bench":32.8,"mindcube_tiny":54.7,"viewspatial":45.5,"site":43.9,"blink":55.29,"3dsrbench":46.34,"embspatial":71.4,"mmsi_video_bench":26.13,"omnispatial_(manual_cot)":39.33,"spar_bench":38.21,"vsi_debiased":53.41},"subScores":{"vsi_bench":{"object_counting":65.68,"object_abs_distance":47,"object_size_estimation":71.78,"room_size_estimation":66.56,"object_rel_distance_accuracy":61.41,"object_rel_direction_accuracy":49.54,"route_planning_accuracy":33.51,"obj_appearance_order_accuracy":69.58},"mmsi_bench":{"pos_cam_cam_accuracy":51.61,"pos_obj_obj_accuracy":29.79,"pos_reg_reg_accuracy":32.1,"pos_cam_obj_accuracy":50,"pos_obj_reg_accuracy":29.41,"pos_cam_reg_accuracy":42.17,"attr_meas_accuracy":37.5,"attr_appr_accuracy":28.79,"motion_cam_accuracy":22.97,"motion_obj_accuracy":34.21,"msr_accuracy":18.69},"mindcube_tiny":{"rotation_accuracy":40,"among_accuracy":54.58,"around_accuracy":66.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":47.94,"camera_perspective_object_view_orientation_accuracy":26.71,"person_perspective_object_view_orientation_accuracy":57.13,"person_perspective_relative_direction_accuracy":43.23,"person_perspective_scene_simulation_relative_direction_accuracy":49.68},"site":{"3d_information_understanding_caa":34.56,"counting_and_existence_caa":55.95,"movement_prediction_and_navigation_caa":28.58,"object_localization_and_positioning_caa":38.95,"spatial_relationship_reasoning_caa":61.77,"multiview_and_crossimage_reasoning_caa":22.04},"blink":{"art_style":75.21,"counting":67.5,"forensic_detection":44.7,"functional_correspondence":33.08,"iq_test":22.67,"jigsaw":72,"multi_view_reasoning":36.84,"object_localization":49.18,"relative_depth":77.42,"relative_reflectance":38.81,"semantic_correspondence":30.94,"spatial_relation":87.41,"visual_correspondence":57.56,"visual_similarity":84.44},"3dsrbench":{"height_higher":44.35,"location_above":45.52,"location_closer_to_camera":74.34,"location_next_to":53.69,"multi_object_closer_to":59.14,"multi_object_facing":59.54,"multi_object_parallel":37.17,"multi_object_same_direction":46.8,"multi_object_viewpoint_towards_object":10.5,"orientation_in_front_of":43.6,"orientation_on_the_left":32.66,"orientation_viewpoint":24.2},"embspatial":{"mp3d_accuracy":73.27,"ai2thor_accuracy":70.3,"scannet_accuracy":70.83},"mmsi_video_bench":{"instance_scene_attribute_accuracy":16.87,"instance_instance_spatial_relationship_accuracy":31.58,"instance_scene_spatial_relationship_accuracy":18.18,"scene_scene_spatial_relationship_accuracy":17.39,"camera_instance_spatial_relationship_accuracy":17.72,"camera_scene_spatial_relationship_accuracy":33.75,"camera_motion_accuracy":30.11,"instance_motion_accuracy":28.89,"interactive_motion_accuracy":19.75,"memoery_update_accuracy":34.31,"multi_view_integration_accuracy":28.57,"planning_accuracy":32.26,"prediction_accuracy":23.17},"omnispatial_(manual_cot)":{"manipulation_accuracy":54.05,"motion_analysis_accuracy":46.24,"traffic_analysis_accuracy":49.41,"localization_accuracy":40.95,"geospatial_strategy_accuracy":40.91,"pattern_recognition_accuracy":24.74,"geometric_reasoning_accuracy":31.61,"egocentric_accuracy":57.84,"allocentric_accuracy":28.99,"hypothetical_accuracy":38.55},"spar_bench":{"depth_prediction_oc":29.42,"depth_prediction_oc_mv":35.22,"depth_prediction_oo":25.48,"depth_prediction_oo_mv":23.71,"distance_prediction_oc":16.16,"distance_prediction_oc_mv":28.49,"distance_prediction_oo":34.68,"distance_prediction_oo_mv":29.16,"position_matching_accuracy":35.88,"camera_motion_infer_accuracy":39.75,"view_change_infer_vci_metric":20.1,"distance_infer_center_oo_accuracy":60.29,"distance_infer_center_oo_mv_accuracy":56.55,"obj_spatial_relation_oc_mv_accuracy":62.75,"obj_spatial_relation_oo_accuracy":55.22,"obj_spatial_relation_oo_mv_accuracy":50.97,"spatial_imagination_oc_accuracy":40.32,"spatial_imagination_oc_mv_accuracy":40.99,"spatial_imagination_oo_accuracy":33.44,"spatial_imagination_oo_mv_accuracy":45.66},"vsi_debiased":{"object_counting":65.68,"object_abs_distance":47,"object_size_estimation":71.78,"room_size_estimation":66.56,"object_rel_distance_accuracy":61.41,"object_rel_direction_accuracy":49.54,"route_planning_accuracy":33.51,"obj_appearance_order_accuracy":69.58}}},{"name":"sensenova_si_1.2_internvl3_8b","displayName":"SenseNova-SI-1.2-InternVL3-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.2-InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":69.6,"mmsi_bench":42.6,"mindcube_tiny":89,"viewspatial":58.8,"site":49,"blink":69.4,"3dsrbench":60.07,"embspatial":77.7,"mmsi_video_bench":26.22,"omnispatial_(manual_cot)":34.77,"spar_bench":49.52,"vsi_debiased":65.17},"subScores":{"vsi_bench":{"object_counting":72.74,"object_abs_distance":56.03,"object_size_estimation":77.12,"room_size_estimation":75.73,"object_rel_distance_accuracy":70.42,"object_rel_direction_accuracy":81.67,"route_planning_accuracy":42.78,"obj_appearance_order_accuracy":79.94},"mmsi_bench":{"pos_cam_cam_accuracy":49.46,"pos_obj_obj_accuracy":50,"pos_reg_reg_accuracy":40.74,"pos_cam_obj_accuracy":68.6,"pos_obj_reg_accuracy":44.71,"pos_cam_reg_accuracy":68.67,"attr_meas_accuracy":39.06,"attr_appr_accuracy":31.82,"motion_cam_accuracy":41.89,"motion_obj_accuracy":26.32,"msr_accuracy":24.75},"mindcube_tiny":{"rotation_accuracy":85.5,"among_accuracy":89.66,"around_accuracy":90.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":74.39,"camera_perspective_object_view_orientation_accuracy":34.74,"person_perspective_object_view_orientation_accuracy":50.9,"person_perspective_relative_direction_accuracy":48.57,"person_perspective_scene_simulation_relative_direction_accuracy":70.23},"site":{"3d_information_understanding_caa":44.84,"counting_and_existence_caa":56.43,"movement_prediction_and_navigation_caa":39.28,"object_localization_and_positioning_caa":50.28,"spatial_relationship_reasoning_caa":60.29,"multiview_and_crossimage_reasoning_caa":36.51},"blink":{"art_style":70.94,"counting":72.5,"forensic_detection":21.97,"functional_correspondence":51.54,"iq_test":24.67,"jigsaw":84.67,"multi_view_reasoning":95.49,"object_localization":58.2,"relative_depth":94.35,"relative_reflectance":32.84,"semantic_correspondence":75.54,"spatial_relation":89.51,"visual_correspondence":97.09,"visual_similarity":96.3},"3dsrbench":{"height_higher":52.03,"location_above":53.9,"location_closer_to_camera":85.25,"location_next_to":63.72,"multi_object_closer_to":75.14,"multi_object_facing":80.35,"multi_object_parallel":51.92,"multi_object_same_direction":52.03,"multi_object_viewpoint_towards_object":41.98,"orientation_in_front_of":69.77,"orientation_on_the_left":51.58,"orientation_viewpoint":32.65},"embspatial":{"mp3d_accuracy":78.93,"ai2thor_accuracy":73.12,"scannet_accuracy":81.17},"mmsi_video_bench":{"instance_scene_attribute_accuracy":21.69,"instance_instance_spatial_relationship_accuracy":39.47,"instance_scene_spatial_relationship_accuracy":29.87,"scene_scene_spatial_relationship_accuracy":26.09,"camera_instance_spatial_relationship_accuracy":26.58,"camera_scene_spatial_relationship_accuracy":30,"camera_motion_accuracy":32.26,"instance_motion_accuracy":17.78,"interactive_motion_accuracy":28.4,"memoery_update_accuracy":27.45,"multi_view_integration_accuracy":17.14,"planning_accuracy":20.97,"prediction_accuracy":25.61},"omnispatial_(manual_cot)":{"manipulation_accuracy":45.95,"motion_analysis_accuracy":40.75,"traffic_analysis_accuracy":42.35,"localization_accuracy":45.71,"geospatial_strategy_accuracy":48.18,"pattern_recognition_accuracy":17.53,"geometric_reasoning_accuracy":28.39,"egocentric_accuracy":66.67,"allocentric_accuracy":20.74,"hypothetical_accuracy":16.87},"spar_bench":{"depth_prediction_oc":70.64,"depth_prediction_oc_mv":57.38,"depth_prediction_oo":15.27,"depth_prediction_oo_mv":21.16,"distance_prediction_oc":59.75,"distance_prediction_oc_mv":57.86,"distance_prediction_oo":53.53,"distance_prediction_oo_mv":38.48,"position_matching_accuracy":50.64,"camera_motion_infer_accuracy":53.5,"view_change_infer_vci_metric":16.14,"distance_infer_center_oo_accuracy":72.94,"distance_infer_center_oo_mv_accuracy":68.75,"obj_spatial_relation_oc_mv_accuracy":64.75,"obj_spatial_relation_oo_accuracy":70.05,"obj_spatial_relation_oo_mv_accuracy":51.25,"spatial_imagination_oc_accuracy":49.46,"spatial_imagination_oc_mv_accuracy":49.42,"spatial_imagination_oo_accuracy":33.11,"spatial_imagination_oo_mv_accuracy":36.41},"vsi_debiased":{"object_counting":72.74,"object_abs_distance":56.03,"object_size_estimation":77.12,"room_size_estimation":75.73,"object_rel_distance_accuracy":70.42,"object_rel_direction_accuracy":81.67,"route_planning_accuracy":42.78,"obj_appearance_order_accuracy":79.94}}},{"name":"sensenova_si_1.3_internvl3_8b","displayName":"SenseNova-SI-1.3-InternVL3-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.3-InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":68.61,"mmsi_bench":42.5,"mindcube_tiny":89.9,"viewspatial":61.31,"site":47.51,"blink":68.02,"3dsrbench":62.4,"embspatial":81.04,"mmsi_video_bench":25.68,"omnispatial_(manual_cot)":35.29,"spar_bench":48.43,"vsi_debiased":63.01},"subScores":{"vsi_bench":{"object_counting":72.04,"object_abs_distance":55.23,"object_size_estimation":77.3,"room_size_estimation":74.06,"object_rel_distance_accuracy":69.3,"object_rel_direction_accuracy":79.46,"route_planning_accuracy":46.91,"obj_appearance_order_accuracy":74.6},"mmsi_bench":{"pos_cam_cam_accuracy":43.01,"pos_obj_obj_accuracy":50,"pos_reg_reg_accuracy":40.74,"pos_cam_obj_accuracy":74.42,"pos_obj_reg_accuracy":44.71,"pos_cam_reg_accuracy":65.06,"attr_meas_accuracy":42.19,"attr_appr_accuracy":25.76,"motion_cam_accuracy":35.14,"motion_obj_accuracy":30.26,"msr_accuracy":28.28},"mindcube_tiny":{"rotation_accuracy":89,"among_accuracy":91.69,"around_accuracy":86.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":74.56,"camera_perspective_object_view_orientation_accuracy":38.65,"person_perspective_object_view_orientation_accuracy":53.92,"person_perspective_relative_direction_accuracy":54.63,"person_perspective_scene_simulation_relative_direction_accuracy":72.22},"site":{"3d_information_understanding_caa":40.76,"counting_and_existence_caa":55.7,"movement_prediction_and_navigation_caa":37.54,"object_localization_and_positioning_caa":48.58,"spatial_relationship_reasoning_caa":58.9,"multiview_and_crossimage_reasoning_caa":35.56},"blink":{"art_style":76.07,"counting":67.5,"forensic_detection":27.27,"functional_correspondence":51.54,"iq_test":23.33,"jigsaw":86.67,"multi_view_reasoning":62.41,"object_localization":59.84,"relative_depth":91.94,"relative_reflectance":39.55,"semantic_correspondence":81.29,"spatial_relation":88.81,"visual_correspondence":97.09,"visual_similarity":92.59},"3dsrbench":{"height_higher":55.22,"location_above":57.37,"location_closer_to_camera":83.48,"location_next_to":63.13,"multi_object_closer_to":74.29,"multi_object_facing":81.21,"multi_object_parallel":50.15,"multi_object_same_direction":58.72,"multi_object_viewpoint_towards_object":41.4,"orientation_in_front_of":70.93,"orientation_on_the_left":68.77,"orientation_viewpoint":35.28},"embspatial":{"mp3d_accuracy":80.18,"ai2thor_accuracy":77.56,"scannet_accuracy":85.5},"mmsi_video_bench":{"instance_scene_attribute_accuracy":25.3,"instance_instance_spatial_relationship_accuracy":40.79,"instance_scene_spatial_relationship_accuracy":23.38,"scene_scene_spatial_relationship_accuracy":26.09,"camera_instance_spatial_relationship_accuracy":24.05,"camera_scene_spatial_relationship_accuracy":13.75,"camera_motion_accuracy":26.88,"instance_motion_accuracy":18.89,"interactive_motion_accuracy":29.63,"memoery_update_accuracy":35.29,"multi_view_integration_accuracy":21.43,"planning_accuracy":25,"prediction_accuracy":21.95},"omnispatial_(manual_cot)":{"manipulation_accuracy":47.3,"motion_analysis_accuracy":43.93,"traffic_analysis_accuracy":36.47,"localization_accuracy":49.52,"geospatial_strategy_accuracy":40.91,"pattern_recognition_accuracy":19.59,"geometric_reasoning_accuracy":29.68,"egocentric_accuracy":59.8,"allocentric_accuracy":21.01,"hypothetical_accuracy":25.3},"spar_bench":{"depth_prediction_oc":70.03,"depth_prediction_oc_mv":58.69,"depth_prediction_oo":12.77,"depth_prediction_oo_mv":22.23,"distance_prediction_oc":55.98,"distance_prediction_oc_mv":57.18,"distance_prediction_oo":54.93,"distance_prediction_oo_mv":38.15,"position_matching_accuracy":56.74,"camera_motion_infer_accuracy":39.5,"view_change_infer_vci_metric":23.24,"distance_infer_center_oo_accuracy":74.12,"distance_infer_center_oo_mv_accuracy":70.54,"obj_spatial_relation_oc_mv_accuracy":69.5,"obj_spatial_relation_oo_accuracy":67.31,"obj_spatial_relation_oo_mv_accuracy":46.81,"spatial_imagination_oc_accuracy":45.43,"spatial_imagination_oc_mv_accuracy":49.42,"spatial_imagination_oo_accuracy":31.46,"spatial_imagination_oo_mv_accuracy":24.65},"vsi_debiased":{"object_counting":72.04,"object_abs_distance":55.23,"object_size_estimation":77.3,"room_size_estimation":74.06,"object_rel_distance_accuracy":69.3,"object_rel_direction_accuracy":79.46,"route_planning_accuracy":46.91,"obj_appearance_order_accuracy":74.6}}},{"name":"gpt_5.2","displayName":"GPT-5.2","link":"https://openai.com/gpt-5/","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":54.49,"mmsi_bench":41.3,"mindcube_tiny":60.38,"viewspatial":47.3,"site":61.9,"blink":71.2,"3dsrbench":60.2,"embspatial":79.3,"mmsi_video_bench":32.28,"omnispatial_(manual_cot)":57.4,"spar_bench":55.07,"vsi_debiased":54.49}},{"name":"internvl3_8b","displayName":"InternVL3-8B","link":"https://huggingface.co/OpenGVLab/InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":42.14,"mmsi_bench":28,"mindcube_tiny":41.54,"viewspatial":38.66,"site":41.15,"blink":53.45,"3dsrbench":44.25,"embspatial":76.35,"mmsi_video_bench":30.2,"omnispatial_(manual_cot)":45.34,"spar_bench":35.86,"vsi_debiased":38.51},"subScores":{"vsi_bench":{"object_counting":66.05,"object_abs_distance":34.89,"object_size_estimation":43.64,"room_size_estimation":47.5,"object_rel_distance_accuracy":48.03,"object_rel_direction_accuracy":39.31,"route_planning_accuracy":26.29,"obj_appearance_order_accuracy":31.39},"mmsi_bench":{"pos_cam_cam_accuracy":22.58,"pos_obj_obj_accuracy":22.34,"pos_reg_reg_accuracy":34.57,"pos_cam_obj_accuracy":31.4,"pos_obj_reg_accuracy":42.35,"pos_cam_reg_accuracy":33.73,"attr_meas_accuracy":25,"attr_appr_accuracy":19.7,"motion_cam_accuracy":20.27,"motion_obj_accuracy":34.21,"msr_accuracy":24.75},"mindcube_tiny":{"rotation_accuracy":36.5,"among_accuracy":38.14,"around_accuracy":53.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":50.31,"camera_perspective_object_view_orientation_accuracy":27.51,"person_perspective_object_view_orientation_accuracy":42.57,"person_perspective_relative_direction_accuracy":37.53,"person_perspective_scene_simulation_relative_direction_accuracy":27.33},"site":{"3d_information_understanding_caa":30.31,"counting_and_existence_caa":57.89,"movement_prediction_and_navigation_caa":26.1,"object_localization_and_positioning_caa":52.41,"spatial_relationship_reasoning_caa":61.94,"multiview_and_crossimage_reasoning_caa":9.92},"blink":{"art_style":67.52,"counting":71.67,"forensic_detection":34.85,"functional_correspondence":28.46,"iq_test":23.33,"jigsaw":78,"multi_view_reasoning":44.36,"object_localization":53.28,"relative_depth":69.35,"relative_reflectance":34.33,"semantic_correspondence":28.06,"spatial_relation":86.71,"visual_correspondence":44.19,"visual_similarity":89.63},"3dsrbench":{"height_higher":49.42,"location_above":58.24,"location_closer_to_camera":76.11,"location_next_to":59.29,"multi_object_closer_to":46.29,"multi_object_facing":37.57,"multi_object_parallel":17.4,"multi_object_same_direction":34.01,"multi_object_viewpoint_towards_object":13.7,"orientation_in_front_of":43.6,"orientation_on_the_left":21.78,"orientation_viewpoint":23.32},"embspatial":{"mp3d_accuracy":76.35,"ai2thor_accuracy":74.25,"scannet_accuracy":78.5},"mmsi_video_bench":{"instance_scene_attribute_accuracy":42.17,"instance_instance_spatial_relationship_accuracy":25,"instance_scene_spatial_relationship_accuracy":40.26,"scene_scene_spatial_relationship_accuracy":23.19,"camera_instance_spatial_relationship_accuracy":22.78,"camera_scene_spatial_relationship_accuracy":31.25,"camera_motion_accuracy":31.18,"instance_motion_accuracy":27.78,"interactive_motion_accuracy":34.57,"memoery_update_accuracy":22.55,"multi_view_integration_accuracy":37.14,"planning_accuracy":30.65,"prediction_accuracy":25.61},"omnispatial_(manual_cot)":{"manipulation_accuracy":58.11,"motion_analysis_accuracy":53.47,"traffic_analysis_accuracy":48.24,"localization_accuracy":53.33,"geospatial_strategy_accuracy":49.09,"pattern_recognition_accuracy":21.65,"geometric_reasoning_accuracy":25.16,"egocentric_accuracy":75.49,"allocentric_accuracy":36.7,"hypothetical_accuracy":49.4},"spar_bench":{"depth_prediction_oc":26.33,"depth_prediction_oc_mv":24.62,"depth_prediction_oo":23.68,"depth_prediction_oo_mv":18.63,"distance_prediction_oc":17.02,"distance_prediction_oc_mv":16.47,"distance_prediction_oo":43.17,"distance_prediction_oo_mv":32.79,"position_matching_accuracy":62.85,"camera_motion_infer_accuracy":36.25,"view_change_infer_vci_metric":18.83,"distance_infer_center_oo_accuracy":66.18,"distance_infer_center_oo_mv_accuracy":60.12,"obj_spatial_relation_oc_mv_accuracy":40.75,"obj_spatial_relation_oo_accuracy":55.22,"obj_spatial_relation_oo_mv_accuracy":37.67,"spatial_imagination_oc_accuracy":29.03,"spatial_imagination_oc_mv_accuracy":41.86,"spatial_imagination_oo_accuracy":28.48,"spatial_imagination_oo_mv_accuracy":37.25},"vsi_debiased":{"object_counting":66.05,"object_abs_distance":34.89,"object_size_estimation":43.64,"room_size_estimation":47.5,"object_rel_distance_accuracy":48.03,"object_rel_direction_accuracy":39.31,"route_planning_accuracy":26.29,"obj_appearance_order_accuracy":31.39}}},{"name":"geothinker","displayName":"GeoThinker","link":"https://huggingface.co/lihy285/GeoThinker","backend":"lmmseval","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":72.6,"mmsi_bench":30.9,"mindcube_tiny":83,"viewspatial":45.9,"site":55.9,"blink":53.9,"3dsrbench":51.9,"embspatial":78.8,"mmsi_video_bench":23.7,"omnispatial_(manual_cot)":40.1,"spar_bench":68.2,"vsi_debiased":null}},{"name":"internvl3_5_2b_instruct","displayName":"InternVL3_5-2B-Instruct","link":"https://huggingface.co/OpenGVLab/InternVL3_5-2B-Instruct","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":51.27,"mmsi_bench":25.4,"mindcube_tiny":42.5,"viewspatial":38.13,"site":35.33,"blink":50.18,"3dsrbench":41.54,"embspatial":61.48,"mmsi_video_bench":25.41,"omnispatial_(manual_cot)":41.1,"spar_bench":32.53,"vsi_debiased":45.72},"subScores":{"vsi_bench":{"object_counting":66.44,"object_abs_distance":39.99,"object_size_estimation":62,"room_size_estimation":42.67,"object_rel_distance_accuracy":53.38,"object_rel_direction_accuracy":46.34,"route_planning_accuracy":40.72,"obj_appearance_order_accuracy":58.58},"mmsi_bench":{"pos_cam_cam_accuracy":20.43,"pos_obj_obj_accuracy":31.91,"pos_reg_reg_accuracy":24.69,"pos_cam_obj_accuracy":30.23,"pos_obj_reg_accuracy":28.24,"pos_cam_reg_accuracy":31.33,"attr_meas_accuracy":20.31,"attr_appr_accuracy":28.79,"motion_cam_accuracy":9.46,"motion_obj_accuracy":34.21,"msr_accuracy":22.22},"mindcube_tiny":{"rotation_accuracy":34,"among_accuracy":43.56,"around_accuracy":46.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":45.63,"camera_perspective_object_view_orientation_accuracy":27.31,"person_perspective_object_view_orientation_accuracy":42.67,"person_perspective_relative_direction_accuracy":39.43,"person_perspective_scene_simulation_relative_direction_accuracy":30.77},"site":{"3d_information_understanding_caa":19.71,"counting_and_existence_caa":46.73,"movement_prediction_and_navigation_caa":26.22,"object_localization_and_positioning_caa":41.64,"spatial_relationship_reasoning_caa":55.7,"multiview_and_crossimage_reasoning_caa":7.49},"blink":{"art_style":62.39,"counting":56.67,"forensic_detection":31.06,"functional_correspondence":17.69,"iq_test":16.67,"jigsaw":64,"multi_view_reasoning":48.87,"object_localization":50.82,"relative_depth":72.58,"relative_reflectance":35.07,"semantic_correspondence":42.45,"spatial_relation":76.92,"visual_correspondence":50.58,"visual_similarity":80},"3dsrbench":{"height_higher":48.26,"location_above":54.62,"location_closer_to_camera":59.44,"location_next_to":57.82,"multi_object_closer_to":50.29,"multi_object_facing":52.02,"multi_object_parallel":37.76,"multi_object_same_direction":40.99,"multi_object_viewpoint_towards_object":7,"orientation_in_front_of":53.2,"orientation_on_the_left":31.23,"orientation_viewpoint":13.41},"embspatial":{"mp3d_accuracy":63.61,"ai2thor_accuracy":58.84,"scannet_accuracy":62.08},"mmsi_video_bench":{"instance_scene_attribute_accuracy":30.12,"instance_instance_spatial_relationship_accuracy":31.58,"instance_scene_spatial_relationship_accuracy":23.38,"scene_scene_spatial_relationship_accuracy":28.99,"camera_instance_spatial_relationship_accuracy":12.66,"camera_scene_spatial_relationship_accuracy":21.25,"camera_motion_accuracy":31.18,"instance_motion_accuracy":30,"interactive_motion_accuracy":32.1,"memoery_update_accuracy":19.61,"multi_view_integration_accuracy":22.86,"planning_accuracy":24.19,"prediction_accuracy":23.17},"spar_bench":{"depth_prediction_oc":43.61,"depth_prediction_oc_mv":28.31,"depth_prediction_oo":20.75,"depth_prediction_oo_mv":21.05,"distance_prediction_oc":11.68,"distance_prediction_oc_mv":6.85,"distance_prediction_oo":43.64,"distance_prediction_oo_mv":31.72,"position_matching_accuracy":47.07,"camera_motion_infer_accuracy":30.5,"view_change_infer_vci_metric":19.84,"distance_infer_center_oo_accuracy":54.41,"distance_infer_center_oo_mv_accuracy":51.79,"obj_spatial_relation_oc_mv_accuracy":54.75,"obj_spatial_relation_oo_accuracy":33.79,"obj_spatial_relation_oo_mv_accuracy":26.87,"spatial_imagination_oc_accuracy":29.84,"spatial_imagination_oc_mv_accuracy":36.34,"spatial_imagination_oo_accuracy":24.5,"spatial_imagination_oo_mv_accuracy":33.33},"vsi_debiased":{"object_counting":48.57,"object_abs_distance":32.44,"object_size_estimation":51.87,"room_size_estimation":37.5,"object_rel_distance_accuracy":50.32,"object_rel_direction_accuracy":40.52,"route_planning_accuracy":48.25,"obj_appearance_order_accuracy":56.29}}},{"name":"qwen3_vl_2b_instruct","displayName":"Qwen3-VL-2B-Instruct","link":"https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":49.7845,"vsi_bench_128frames":54.3881,"mmsi_bench":28.9,"mindcube_tiny":34.52,"viewspatial":36.97,"site":35.66,"blink":53.18,"3dsrbench":47.45,"embspatial":70.11,"mmsi_video_bench":26.58,"omnispatial_(manual_cot)":34.64,"spar_bench":33.92,"vsi_debiased":43.28},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":57.4434,"object_abs_distance":39.4964,"object_counting":58.0531,"object_rel_direction_accuracy":40.2577,"object_rel_distance_accuracy":52.9577,"object_size_estimation":70,"room_size_estimation":53.2639,"route_planning_accuracy":26.8041},"vsi_bench_128frames":{"obj_appearance_order_accuracy":65.0485,"object_abs_distance":42.6499,"object_counting":63.1858,"object_rel_direction_accuracy":43.7137,"object_rel_distance_accuracy":58.0282,"object_size_estimation":73.851,"room_size_estimation":53.5764,"route_planning_accuracy":35.0515},"mmsi_bench":{"pos_cam_cam_accuracy":26.88,"pos_obj_obj_accuracy":29.79,"pos_reg_reg_accuracy":30.86,"pos_cam_obj_accuracy":38.37,"pos_obj_reg_accuracy":35.29,"pos_cam_reg_accuracy":33.73,"attr_meas_accuracy":23.44,"attr_appr_accuracy":28.79,"motion_cam_accuracy":29.73,"motion_obj_accuracy":28.95,"msr_accuracy":21.21},"mindcube_tiny":{"rotation_accuracy":32.5,"among_accuracy":31.69,"around_accuracy":42.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":49.63,"camera_perspective_object_view_orientation_accuracy":23.8,"person_perspective_object_view_orientation_accuracy":35.34,"person_perspective_relative_direction_accuracy":32.66,"person_perspective_scene_simulation_relative_direction_accuracy":33.3},"site":{"3d_information_understanding_caa":26.07,"counting_and_existence_caa":43.58,"movement_prediction_and_navigation_caa":18.88,"object_localization_and_positioning_caa":45.75,"spatial_relationship_reasoning_caa":57,"multiview_and_crossimage_reasoning_caa":14.42},"blink":{"art_style":65.81,"counting":62.5,"forensic_detection":34.09,"functional_correspondence":33.08,"iq_test":1.33,"jigsaw":54,"multi_view_reasoning":55.64,"object_localization":59.84,"relative_depth":70.97,"relative_reflectance":30.6,"semantic_correspondence":58.99,"spatial_relation":81.12,"visual_correspondence":63.37,"visual_similarity":77.78},"3dsrbench":{"height_higher":50,"location_above":57.8,"location_closer_to_camera":74.93,"location_next_to":57.82,"multi_object_closer_to":56.57,"multi_object_facing":50,"multi_object_parallel":48.67,"multi_object_same_direction":45.35,"multi_object_viewpoint_towards_object":4.37,"orientation_in_front_of":47.09,"orientation_on_the_left":26.07,"orientation_viewpoint":11.08},"embspatial":{"mp3d_accuracy":72.19,"ai2thor_accuracy":67.47,"scannet_accuracy":70.75},"mmsi_video_bench":{"instance_scene_attribute_accuracy":34.94,"instance_instance_spatial_relationship_accuracy":30.26,"instance_scene_spatial_relationship_accuracy":23.38,"scene_scene_spatial_relationship_accuracy":27.54,"camera_instance_spatial_relationship_accuracy":16.46,"camera_scene_spatial_relationship_accuracy":32.5,"camera_motion_accuracy":26.88,"instance_motion_accuracy":28.89,"interactive_motion_accuracy":28.4,"memoery_update_accuracy":22.55,"multi_view_integration_accuracy":17.14,"planning_accuracy":22.58,"prediction_accuracy":35.37},"omnispatial_(manual_cot)":{"manipulation_accuracy":52.7,"motion_analysis_accuracy":26.01,"traffic_analysis_accuracy":44.71,"localization_accuracy":54.29,"geospatial_strategy_accuracy":41.82,"pattern_recognition_accuracy":14.43,"geometric_reasoning_accuracy":20.65,"egocentric_accuracy":61.76,"allocentric_accuracy":30.85,"hypothetical_accuracy":43.37},"spar_bench":{"depth_prediction_oc":22,"depth_prediction_oc_mv":26.06,"depth_prediction_oo":19.49,"depth_prediction_oo_mv":24.22,"distance_prediction_oc":4.83,"distance_prediction_oc_mv":11.26,"distance_prediction_oo":44.05,"distance_prediction_oo_mv":40.51,"position_matching_accuracy":48.09,"camera_motion_infer_accuracy":28.5,"view_change_infer_vci_metric":14.32,"distance_infer_center_oo_accuracy":61.18,"distance_infer_center_oo_mv_accuracy":61.31,"obj_spatial_relation_oc_mv_accuracy":55.25,"obj_spatial_relation_oo_accuracy":45.88,"obj_spatial_relation_oo_mv_accuracy":40.44,"spatial_imagination_oc_accuracy":34.95,"spatial_imagination_oc_mv_accuracy":33.43,"spatial_imagination_oo_accuracy":26.49,"spatial_imagination_oo_mv_accuracy":36.13},"vsi_debiased":{"object_counting":62.18,"object_abs_distance":40.26,"object_size_estimation":71.46,"room_size_estimation":49.79,"object_rel_distance_accuracy":52.25,"object_rel_direction_accuracy":42.01,"route_planning_accuracy":30.41,"obj_appearance_order_accuracy":54.53}}},{"name":"vilasr","displayName":"ViLaSR","link":"https://huggingface.co/inclusionAI/ViLaSR","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":44.63,"mmsi_bench":30.2,"mindcube_tiny":35.1,"viewspatial":35.71,"site":38.74,"blink":51.39,"3dsrbench":46.56,"embspatial":67.31,"mmsi_video_bench":28.3,"omnispatial_(manual_cot)":19.24,"spar_bench":37.36,"vsi_debiased":38.26},"subScores":{"vsi_bench":{"object_counting":58.11,"object_abs_distance":33.88,"object_size_estimation":61.44,"room_size_estimation":28.89,"object_rel_distance_accuracy":45.07,"object_rel_direction_accuracy":46.5,"route_planning_accuracy":29.9,"obj_appearance_order_accuracy":53.24},"mmsi_bench":{"pos_cam_cam_accuracy":29.03,"pos_obj_obj_accuracy":35.11,"pos_reg_reg_accuracy":28.4,"pos_cam_obj_accuracy":39.53,"pos_obj_reg_accuracy":40,"pos_cam_reg_accuracy":44.58,"attr_meas_accuracy":31.25,"attr_appr_accuracy":16.67,"motion_cam_accuracy":17.57,"motion_obj_accuracy":31.58,"msr_accuracy":23.23},"mindcube_tiny":{"rotation_accuracy":35.5,"among_accuracy":31.02,"around_accuracy":44.4},"viewspatial":{"camera_perspective_relative_direction_accuracy":46.81,"camera_perspective_object_view_orientation_accuracy":25.3,"person_perspective_object_view_orientation_accuracy":39.06,"person_perspective_relative_direction_accuracy":32.66,"person_perspective_scene_simulation_relative_direction_accuracy":26.61},"site":{"3d_information_understanding_caa":19.38,"counting_and_existence_caa":54.9,"movement_prediction_and_navigation_caa":22.99,"object_localization_and_positioning_caa":43.2,"spatial_relationship_reasoning_caa":64.37,"multiview_and_crossimage_reasoning_caa":12.43},"blink":{"art_style":68.38,"counting":70,"forensic_detection":55.3,"functional_correspondence":26.15,"iq_test":18,"jigsaw":63.33,"multi_view_reasoning":48.12,"object_localization":40.16,"relative_depth":74.19,"relative_reflectance":12.69,"semantic_correspondence":19.42,"spatial_relation":86.71,"visual_correspondence":55.23,"visual_similarity":85.93},"3dsrbench":{"height_higher":38.26,"location_above":65.75,"location_closer_to_camera":66.37,"location_next_to":50.44,"multi_object_closer_to":45.43,"multi_object_facing":59.54,"multi_object_parallel":47.79,"multi_object_same_direction":45.35,"multi_object_viewpoint_towards_object":3.5,"orientation_in_front_of":52.33,"orientation_on_the_left":33.52,"orientation_viewpoint":20.12},"embspatial":{"mp3d_accuracy":69.53,"ai2thor_accuracy":67.88,"scannet_accuracy":64.5},"mmsi_video_bench":{"instance_scene_attribute_accuracy":26.51,"instance_instance_spatial_relationship_accuracy":36.84,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":21.74,"camera_instance_spatial_relationship_accuracy":21.52,"camera_scene_spatial_relationship_accuracy":28.75,"camera_motion_accuracy":33.33,"instance_motion_accuracy":24.44,"interactive_motion_accuracy":30.86,"memoery_update_accuracy":33.33,"multi_view_integration_accuracy":24.29,"planning_accuracy":25,"prediction_accuracy":35.37},"omnispatial_(manual_cot)":{"manipulation_accuracy":51.35,"motion_analysis_accuracy":13.29,"traffic_analysis_accuracy":31.76,"localization_accuracy":24.76,"geospatial_strategy_accuracy":12.73,"pattern_recognition_accuracy":21.65,"geometric_reasoning_accuracy":14.19,"egocentric_accuracy":23.53,"allocentric_accuracy":13.3,"hypothetical_accuracy":32.53},"spar_bench":{"depth_prediction_oc":41.94,"depth_prediction_oc_mv":40.06,"depth_prediction_oo":17.66,"depth_prediction_oo_mv":19.6,"distance_prediction_oc":48.63,"distance_prediction_oc_mv":43.21,"distance_prediction_oo":37.71,"distance_prediction_oo_mv":33.67,"position_matching_accuracy":44.02,"camera_motion_infer_accuracy":25.25,"view_change_infer_vci_metric":17.84,"distance_infer_center_oo_accuracy":61.47,"distance_infer_center_oo_mv_accuracy":55.06,"obj_spatial_relation_oc_mv_accuracy":46.75,"obj_spatial_relation_oo_accuracy":48.08,"obj_spatial_relation_oo_mv_accuracy":38.78,"spatial_imagination_oc_accuracy":32.26,"spatial_imagination_oc_mv_accuracy":37.5,"spatial_imagination_oo_accuracy":26.49,"spatial_imagination_oo_mv_accuracy":31.37},"vsi_debiased":{"object_counting":58.11,"object_abs_distance":33.88,"object_size_estimation":61.44,"room_size_estimation":28.89,"object_rel_distance_accuracy":45.07,"object_rel_direction_accuracy":46.5,"route_planning_accuracy":29.9,"obj_appearance_order_accuracy":53.24}}},{"name":"spatialladder_3b","displayName":"SpatialLadder-3B","link":"https://huggingface.co/hongxingli/SpatialLadder-3B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":44.86,"mmsi_bench":27.4,"mindcube_tiny":43.46,"viewspatial":39.85,"site":27.96,"blink":42.97,"3dsrbench":42.76,"embspatial":58.24,"mmsi_video_bench":27.4,"omnispatial_(manual_cot)":41.88,"spar_bench":32.94,"vsi_debiased":35.2},"subScores":{"vsi_bench":{"object_counting":62.16,"object_abs_distance":35.35,"object_size_estimation":61.99,"room_size_estimation":41.42,"object_rel_distance_accuracy":45.63,"object_rel_direction_accuracy":46.46,"route_planning_accuracy":27.32,"obj_appearance_order_accuracy":38.51},"mmsi_bench":{"pos_cam_cam_accuracy":36.56,"pos_obj_obj_accuracy":29.79,"pos_reg_reg_accuracy":29.63,"pos_cam_obj_accuracy":32.56,"pos_obj_reg_accuracy":30.59,"pos_cam_reg_accuracy":24.1,"attr_meas_accuracy":18.75,"attr_appr_accuracy":31.82,"motion_cam_accuracy":22.97,"motion_obj_accuracy":23.68,"msr_accuracy":23.23},"mindcube_tiny":{"rotation_accuracy":35,"among_accuracy":43.22,"around_accuracy":50.8},"viewspatial":{"camera_perspective_relative_direction_accuracy":46.25,"camera_perspective_object_view_orientation_accuracy":25.7,"person_perspective_object_view_orientation_accuracy":56.22,"person_perspective_relative_direction_accuracy":31.95,"person_perspective_scene_simulation_relative_direction_accuracy":33.57},"site":{"3d_information_understanding_caa":17.42,"counting_and_existence_caa":44.95,"movement_prediction_and_navigation_caa":11.29,"object_localization_and_positioning_caa":32.01,"spatial_relationship_reasoning_caa":47.29,"multiview_and_crossimage_reasoning_caa":2.9},"blink":{"art_style":53.85,"counting":53.33,"forensic_detection":22.73,"functional_correspondence":23.85,"iq_test":26.67,"jigsaw":49.33,"multi_view_reasoning":44.36,"object_localization":50,"relative_depth":58.06,"relative_reflectance":31.34,"semantic_correspondence":32.37,"spatial_relation":75.52,"visual_correspondence":29.07,"visual_similarity":57.78},"3dsrbench":{"height_higher":45.07,"location_above":39.88,"location_closer_to_camera":65.34,"location_next_to":47.49,"multi_object_closer_to":46.86,"multi_object_facing":58.96,"multi_object_parallel":45.13,"multi_object_same_direction":48.84,"multi_object_viewpoint_towards_object":8.75,"orientation_in_front_of":39.83,"orientation_on_the_left":34.38,"orientation_viewpoint":11.08},"embspatial":{"mp3d_accuracy":59.95,"ai2thor_accuracy":54.08,"scannet_accuracy":60.83},"mmsi_video_bench":{"instance_scene_attribute_accuracy":32.53,"instance_instance_spatial_relationship_accuracy":34.21,"instance_scene_spatial_relationship_accuracy":29.87,"scene_scene_spatial_relationship_accuracy":23.19,"camera_instance_spatial_relationship_accuracy":15.19,"camera_scene_spatial_relationship_accuracy":32.5,"camera_motion_accuracy":30.11,"instance_motion_accuracy":30,"interactive_motion_accuracy":35.8,"memoery_update_accuracy":29.41,"multi_view_integration_accuracy":22.86,"planning_accuracy":20.16,"prediction_accuracy":21.95},"omnispatial_(manual_cot)":{"manipulation_accuracy":60.81,"motion_analysis_accuracy":43.93,"traffic_analysis_accuracy":44.71,"localization_accuracy":35.24,"geospatial_strategy_accuracy":40,"pattern_recognition_accuracy":31.96,"geometric_reasoning_accuracy":27.74,"egocentric_accuracy":68.63,"allocentric_accuracy":40.16,"hypothetical_accuracy":37.35},"spar_bench":{"depth_prediction_oc":27,"depth_prediction_oc_mv":26.38,"depth_prediction_oo":24.11,"depth_prediction_oo_mv":21.88,"distance_prediction_oc":10.43,"distance_prediction_oc_mv":21.59,"distance_prediction_oo":32.67,"distance_prediction_oo_mv":34.75,"position_matching_accuracy":46.31,"camera_motion_infer_accuracy":28.25,"view_change_infer_vci_metric":13.63,"distance_infer_center_oo_accuracy":56.76,"distance_infer_center_oo_mv_accuracy":53.57,"obj_spatial_relation_oc_mv_accuracy":51.75,"obj_spatial_relation_oo_accuracy":39.29,"obj_spatial_relation_oo_mv_accuracy":39.06,"spatial_imagination_oc_accuracy":34.14,"spatial_imagination_oc_mv_accuracy":39.53,"spatial_imagination_oo_accuracy":23.84,"spatial_imagination_oo_mv_accuracy":33.89},"vsi_debiased":{"object_counting":62.16,"object_abs_distance":35.35,"object_size_estimation":61.99,"room_size_estimation":41.42,"object_rel_distance_accuracy":45.63,"object_rel_direction_accuracy":46.46,"route_planning_accuracy":27.32,"obj_appearance_order_accuracy":38.51}}},{"name":"spacer_sft_7b","displayName":"SpaceR-SFT-7B","link":"https://huggingface.co/RUBBISHLIKE/SpaceR-SFT-7B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":41.56,"mmsi_bench":27.4,"mindcube_tiny":37.98,"viewspatial":35.85,"site":34.27,"blink":49.61,"3dsrbench":40.45,"embspatial":66.92,"mmsi_video_bench":24.68,"omnispatial_(manual_cot)":40.97,"spar_bench":34.19,"vsi_debiased":31.56},"subScores":{"vsi_bench":{"object_counting":30.04,"object_abs_distance":25.24,"object_size_estimation":46.98,"room_size_estimation":29.55,"object_rel_distance_accuracy":40.28,"object_rel_direction_accuracy":46.47,"route_planning_accuracy":32.47,"obj_appearance_order_accuracy":39.32},"mmsi_bench":{"pos_cam_cam_accuracy":25.81,"pos_obj_obj_accuracy":31.91,"pos_reg_reg_accuracy":29.63,"pos_cam_obj_accuracy":25.58,"pos_obj_reg_accuracy":31.76,"pos_cam_reg_accuracy":22.89,"attr_meas_accuracy":26.56,"attr_appr_accuracy":28.79,"motion_cam_accuracy":16.22,"motion_obj_accuracy":34.21,"msr_accuracy":27.27},"mindcube_tiny":{"rotation_accuracy":35,"among_accuracy":34.24,"around_accuracy":49.2},"viewspatial":{"camera_perspective_relative_direction_accuracy":43.2,"camera_perspective_object_view_orientation_accuracy":28.92,"person_perspective_object_view_orientation_accuracy":37.45,"person_perspective_relative_direction_accuracy":34.09,"person_perspective_scene_simulation_relative_direction_accuracy":30.23},"site":{"3d_information_understanding_caa":16.44,"counting_and_existence_caa":49.64,"movement_prediction_and_navigation_caa":16.02,"object_localization_and_positioning_caa":38.95,"spatial_relationship_reasoning_caa":60.21,"multiview_and_crossimage_reasoning_caa":9.14},"blink":{"art_style":76.07,"counting":65,"forensic_detection":32.58,"functional_correspondence":20,"iq_test":4,"jigsaw":60,"multi_view_reasoning":43.61,"object_localization":52.46,"relative_depth":66.13,"relative_reflectance":31.34,"semantic_correspondence":35.25,"spatial_relation":80.42,"visual_correspondence":51.16,"visual_similarity":83.7},"3dsrbench":{"height_higher":36.38,"location_above":47.25,"location_closer_to_camera":63.13,"location_next_to":44.54,"multi_object_closer_to":42.86,"multi_object_facing":52.31,"multi_object_parallel":24.19,"multi_object_same_direction":47.97,"multi_object_viewpoint_towards_object":3.79,"orientation_in_front_of":54.36,"orientation_on_the_left":27.22,"orientation_viewpoint":16.33},"embspatial":{"mp3d_accuracy":67.78,"ai2thor_accuracy":66.67,"scannet_accuracy":66.33},"mmsi_video_bench":{"instance_scene_attribute_accuracy":28.92,"instance_instance_spatial_relationship_accuracy":35.53,"instance_scene_spatial_relationship_accuracy":22.08,"scene_scene_spatial_relationship_accuracy":23.19,"camera_instance_spatial_relationship_accuracy":21.52,"camera_scene_spatial_relationship_accuracy":26.25,"camera_motion_accuracy":29.03,"instance_motion_accuracy":18.89,"interactive_motion_accuracy":19.75,"memoery_update_accuracy":25.49,"multi_view_integration_accuracy":20,"planning_accuracy":23.39,"prediction_accuracy":26.83},"omnispatial_(manual_cot)":{"manipulation_accuracy":60.81,"motion_analysis_accuracy":39.6,"traffic_analysis_accuracy":48.24,"localization_accuracy":45.71,"geospatial_strategy_accuracy":42.73,"pattern_recognition_accuracy":23.71,"geometric_reasoning_accuracy":25.16,"egocentric_accuracy":70.59,"allocentric_accuracy":36.97,"hypothetical_accuracy":44.58},"spar_bench":{"depth_prediction_oc":35.67,"depth_prediction_oc_mv":39.97,"depth_prediction_oo":16.37,"depth_prediction_oo_mv":15.78,"distance_prediction_oc":22.6,"distance_prediction_oc_mv":23.51,"distance_prediction_oo":31.29,"distance_prediction_oo_mv":30.34,"position_matching_accuracy":34.1,"camera_motion_infer_accuracy":20.75,"view_change_infer_vci_metric":16.67,"distance_infer_center_oo_accuracy":55,"distance_infer_center_oo_mv_accuracy":52.98,"obj_spatial_relation_oc_mv_accuracy":49.5,"obj_spatial_relation_oo_accuracy":48.08,"obj_spatial_relation_oo_mv_accuracy":47.09,"spatial_imagination_oc_accuracy":33.6,"spatial_imagination_oc_mv_accuracy":34.88,"spatial_imagination_oo_accuracy":31.13,"spatial_imagination_oo_mv_accuracy":44.54},"vsi_debiased":{"object_counting":30.04,"object_abs_distance":25.24,"object_size_estimation":46.98,"room_size_estimation":29.55,"object_rel_distance_accuracy":40.28,"object_rel_direction_accuracy":46.47,"route_planning_accuracy":32.47,"obj_appearance_order_accuracy":39.32}}},{"name":"qwen2.5_vl_7b_instruct","displayName":"Qwen2.5-VL-7B-Instruct","link":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":37.8047,"vsi_bench_128frames":33.6701,"mmsi_bench":26.8,"mindcube_tiny":36.05,"viewspatial":36.85,"site":37.64,"blink":55.87,"3dsrbench":47.51,"embspatial":71.84,"mmsi_video_bench":27.12,"omnispatial_(manual_cot)":37.38,"spar_bench":33.83,"vsi_debiased":28.89},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":34.7896,"object_abs_distance":22.6259,"object_counting":40.8496,"object_rel_direction_accuracy":40.7361,"object_rel_distance_accuracy":37.8873,"object_size_estimation":48.9507,"room_size_estimation":46.7014,"route_planning_accuracy":29.8969},"vsi_bench_128frames":{"obj_appearance_order_accuracy":33.0097,"object_abs_distance":20.8993,"object_counting":31.469,"object_rel_direction_accuracy":33.5732,"object_rel_distance_accuracy":35.6338,"object_size_estimation":50.5037,"room_size_estimation":34.375,"route_planning_accuracy":29.8969},"mmsi_bench":{"pos_cam_cam_accuracy":27.96,"pos_obj_obj_accuracy":26.6,"pos_reg_reg_accuracy":19.75,"pos_cam_obj_accuracy":32.56,"pos_obj_reg_accuracy":38.82,"pos_cam_reg_accuracy":28.92,"attr_meas_accuracy":23.44,"attr_appr_accuracy":21.21,"motion_cam_accuracy":20.27,"motion_obj_accuracy":30.26,"msr_accuracy":24.75},"mindcube_tiny":{"rotation_accuracy":37,"among_accuracy":32.37,"around_accuracy":44},"viewspatial":{"camera_perspective_relative_direction_accuracy":46.76,"camera_perspective_object_view_orientation_accuracy":31.22,"person_perspective_object_view_orientation_accuracy":39.96,"person_perspective_relative_direction_accuracy":32.42,"person_perspective_scene_simulation_relative_direction_accuracy":26.61},"site":{"3d_information_understanding_caa":19.05,"counting_and_existence_caa":54.33,"movement_prediction_and_navigation_caa":15.65,"object_localization_and_positioning_caa":45.61,"spatial_relationship_reasoning_caa":63.76,"multiview_and_crossimage_reasoning_caa":12},"blink":{"art_style":71.79,"counting":71.67,"forensic_detection":47.73,"functional_correspondence":23.85,"iq_test":26.67,"jigsaw":56,"multi_view_reasoning":55.64,"object_localization":52.46,"relative_depth":79.03,"relative_reflectance":38.06,"semantic_correspondence":36.69,"spatial_relation":88.81,"visual_correspondence":52.33,"visual_similarity":88.15},"3dsrbench":{"height_higher":44.93,"location_above":50.87,"location_closer_to_camera":74.34,"location_next_to":56.05,"multi_object_closer_to":48.29,"multi_object_facing":51.16,"multi_object_parallel":37.76,"multi_object_same_direction":47.67,"multi_object_viewpoint_towards_object":9.91,"orientation_in_front_of":56.1,"orientation_on_the_left":34.38,"orientation_viewpoint":31.78},"embspatial":{"mp3d_accuracy":74.6,"ai2thor_accuracy":70.54,"scannet_accuracy":70.42},"mmsi_video_bench":{"instance_scene_attribute_accuracy":24.1,"instance_instance_spatial_relationship_accuracy":35.53,"instance_scene_spatial_relationship_accuracy":24.68,"scene_scene_spatial_relationship_accuracy":18.84,"camera_instance_spatial_relationship_accuracy":21.52,"camera_scene_spatial_relationship_accuracy":30,"camera_motion_accuracy":22.58,"instance_motion_accuracy":21.11,"interactive_motion_accuracy":27.16,"memoery_update_accuracy":29.41,"multi_view_integration_accuracy":30,"planning_accuracy":33.87,"prediction_accuracy":30.49},"omnispatial_(manual_cot)":{"manipulation_accuracy":58.11,"motion_analysis_accuracy":28.32,"traffic_analysis_accuracy":45.88,"localization_accuracy":49.52,"geospatial_strategy_accuracy":48.18,"pattern_recognition_accuracy":23.71,"geometric_reasoning_accuracy":32.26,"egocentric_accuracy":61.76,"allocentric_accuracy":30.32,"hypothetical_accuracy":45.78},"spar_bench":{"depth_prediction_oc":32.19,"depth_prediction_oc_mv":34.91,"depth_prediction_oo":21.83,"depth_prediction_oo_mv":14.38,"distance_prediction_oc":42.47,"distance_prediction_oc_mv":28.66,"distance_prediction_oo":23.33,"distance_prediction_oo_mv":23.1,"position_matching_accuracy":41.22,"camera_motion_infer_accuracy":23.75,"view_change_infer_vci_metric":17.73,"distance_infer_center_oo_accuracy":57.35,"distance_infer_center_oo_mv_accuracy":55.95,"obj_spatial_relation_oc_mv_accuracy":44.25,"obj_spatial_relation_oo_accuracy":49.45,"obj_spatial_relation_oo_mv_accuracy":37.67,"spatial_imagination_oc_accuracy":32.26,"spatial_imagination_oc_mv_accuracy":33.72,"spatial_imagination_oo_accuracy":29.14,"spatial_imagination_oo_mv_accuracy":33.33},"vsi_debiased":{"object_counting":32.88,"object_abs_distance":18.17,"object_size_estimation":43.88,"room_size_estimation":31.7,"object_rel_distance_accuracy":38.03,"object_rel_direction_accuracy":37.42,"route_planning_accuracy":28.35,"obj_appearance_order_accuracy":27.99}}},{"name":"internvl3_2b","displayName":"InternVL3-2B","link":"https://huggingface.co/OpenGVLab/InternVL3-2B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":32.98,"mmsi_bench":26.5,"mindcube_tiny":37.5,"viewspatial":32.56,"site":30.03,"blink":50.76,"3dsrbench":47.68,"embspatial":60.11,"mmsi_video_bench":29.11,"omnispatial_(manual_cot)":42.01,"spar_bench":27.22,"vsi_debiased":28.6},"subScores":{"vsi_bench":{"object_counting":64.8,"object_abs_distance":30.86,"object_size_estimation":32.41,"room_size_estimation":22.99,"object_rel_distance_accuracy":32.25,"object_rel_direction_accuracy":34.9,"route_planning_accuracy":32.99,"obj_appearance_order_accuracy":12.62},"mmsi_bench":{"pos_cam_cam_accuracy":31.18,"pos_obj_obj_accuracy":22.34,"pos_reg_reg_accuracy":28.4,"pos_cam_obj_accuracy":30.23,"pos_obj_reg_accuracy":28.24,"pos_cam_reg_accuracy":28.92,"attr_meas_accuracy":25,"attr_appr_accuracy":22.73,"motion_cam_accuracy":16.22,"motion_obj_accuracy":28.95,"msr_accuracy":26.77},"mindcube_tiny":{"rotation_accuracy":29,"among_accuracy":36.95,"around_accuracy":45.6},"viewspatial":{"camera_perspective_relative_direction_accuracy":42.02,"camera_perspective_object_view_orientation_accuracy":17.57,"person_perspective_object_view_orientation_accuracy":38.86,"person_perspective_relative_direction_accuracy":34.56,"person_perspective_scene_simulation_relative_direction_accuracy":23.71},"site":{"3d_information_understanding_caa":13.83,"counting_and_existence_caa":46.49,"movement_prediction_and_navigation_caa":9.8,"object_localization_and_positioning_caa":40.37,"spatial_relationship_reasoning_caa":50.93,"multiview_and_crossimage_reasoning_caa":5.67},"blink":{"art_style":56.41,"counting":73.33,"forensic_detection":18.94,"functional_correspondence":26.92,"iq_test":24,"jigsaw":75.33,"multi_view_reasoning":59.4,"object_localization":62.3,"relative_depth":70.97,"relative_reflectance":34.33,"semantic_correspondence":23.74,"spatial_relation":79.02,"visual_correspondence":34.3,"visual_similarity":80},"3dsrbench":{"height_higher":50,"location_above":54.19,"location_closer_to_camera":61.8,"location_next_to":55.75,"multi_object_closer_to":53.43,"multi_object_facing":45.38,"multi_object_parallel":50.44,"multi_object_same_direction":52.62,"multi_object_viewpoint_towards_object":12.54,"orientation_in_front_of":53.2,"orientation_on_the_left":34.1,"orientation_viewpoint":26.24},"embspatial":{"mp3d_accuracy":60.78,"ai2thor_accuracy":55.77,"scannet_accuracy":63.92},"mmsi_video_bench":{"instance_scene_attribute_accuracy":24.1,"instance_instance_spatial_relationship_accuracy":22.37,"instance_scene_spatial_relationship_accuracy":37.66,"scene_scene_spatial_relationship_accuracy":26.09,"camera_instance_spatial_relationship_accuracy":24.05,"camera_scene_spatial_relationship_accuracy":30,"camera_motion_accuracy":31.18,"instance_motion_accuracy":25.56,"interactive_motion_accuracy":33.33,"memoery_update_accuracy":33.33,"multi_view_integration_accuracy":35.71,"planning_accuracy":24.19,"prediction_accuracy":32.93},"omnispatial_(manual_cot)":{"manipulation_accuracy":64.86,"motion_analysis_accuracy":45.66,"traffic_analysis_accuracy":51.76,"localization_accuracy":42.86,"geospatial_strategy_accuracy":40.91,"pattern_recognition_accuracy":18.56,"geometric_reasoning_accuracy":29.03,"egocentric_accuracy":63.73,"allocentric_accuracy":36.17,"hypothetical_accuracy":48.19},"spar_bench":{"depth_prediction_oc":15.33,"depth_prediction_oc_mv":13.16,"depth_prediction_oo":21.72,"depth_prediction_oo_mv":21.56,"distance_prediction_oc":12.29,"distance_prediction_oc_mv":9.73,"distance_prediction_oo":29.78,"distance_prediction_oo_mv":24.55,"position_matching_accuracy":37.91,"camera_motion_infer_accuracy":22.75,"view_change_infer_vci_metric":16.3,"distance_infer_center_oo_accuracy":52.06,"distance_infer_center_oo_mv_accuracy":47.92,"obj_spatial_relation_oc_mv_accuracy":43.25,"obj_spatial_relation_oo_accuracy":37.64,"obj_spatial_relation_oo_mv_accuracy":21.88,"spatial_imagination_oc_accuracy":28.49,"spatial_imagination_oc_mv_accuracy":34.88,"spatial_imagination_oo_accuracy":25.17,"spatial_imagination_oo_mv_accuracy":28.01},"vsi_debiased":{"object_counting":64.8,"object_abs_distance":30.86,"object_size_estimation":32.41,"room_size_estimation":22.99,"object_rel_distance_accuracy":32.25,"object_rel_direction_accuracy":34.9,"route_planning_accuracy":32.99,"obj_appearance_order_accuracy":12.62}}},{"name":"sensenova-u1-8b-mot","displayName":"SenseNova-U1-8B-MoT","link":"https://huggingface.co/sensenova/SenseNova-U1-8B-MoT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":57.5446,"mmsi_bench":38,"mindcube_tiny":61.8269,"viewspatial":55.8123,"site":49.343,"blink":63.2825,"3dsrbench":63.4477,"embspatial":79.3407,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":63.1068,"object_abs_distance":42.53,"object_counting":63.3451,"object_rel_direction_accuracy":56.9984,"object_rel_distance_accuracy":52.8169,"object_size_estimation":73.2424,"room_size_estimation":63.4722,"route_planning_accuracy":44.8454},"mmsi_bench":{"attr_appr_accuracy":21.2121,"attr_meas_accuracy":43.75,"motion_cam_accuracy":25.6757,"motion_obj_accuracy":31.5789,"msr_accuracy":26.7677,"pos_cam_cam_accuracy":46.2366,"pos_cam_obj_accuracy":58.1395,"pos_cam_reg_accuracy":63.8554,"pos_obj_obj_accuracy":41.4894,"pos_obj_reg_accuracy":38.8235,"pos_reg_reg_accuracy":29.6296},"mindcube_tiny":{"among_accuracy":51.3559,"around_accuracy":64.8,"rotation_accuracy":89},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":38.4538,"camera_perspective_relative_direction_accuracy":66.2155,"person_perspective_object_view_orientation_accuracy":47.3896,"person_perspective_relative_direction_accuracy":51.5439,"person_perspective_scene_simulation_relative_direction_accuracy":65.6109},"site":{"3d_information_understanding_caa":46.634,"counting_and_existence_caa":53.6832,"movement_prediction_and_navigation_caa":31.0731,"multiview_and_crossimage_reasoning_caa":35.3823,"object_localization_and_positioning_caa":64.5892,"spatial_relationship_reasoning_caa":63.4997},"blink":{"art_style":75.2137,"counting":71.6667,"forensic_detection":47.7273,"functional_correspondence":58.4615,"iq_test":28.6667,"jigsaw":50.6667,"multi_view_reasoning":35.3383,"object_localization":67.2131,"relative_depth":84.6774,"relative_reflectance":33.5821,"semantic_correspondence":66.9065,"spatial_relation":90.2098,"visual_correspondence":88.9535,"visual_similarity":86.6667},"3dsrbench":{"height_higher":52.7536,"location_above":63.4393,"location_closer_to_camera":85.6932,"location_next_to":73.7463,"multi_object_closer_to":74.2857,"multi_object_facing":74.8555,"multi_object_parallel":49.2625,"multi_object_same_direction":51.1628,"multi_object_viewpoint_towards_object":41.3994,"orientation_in_front_of":77.6163,"orientation_on_the_left":56.7335,"orientation_viewpoint":49.2711},"embspatial":{"ai2thor_accuracy":74.4956,"mp3d_accuracy":81.3489,"scannet_accuracy":82.3333}}},{"name":"gemma-4-26B-A4B","displayName":"gemma-4-26B-A4B","link":"https://huggingface.co/google/gemma-4-26B-A4B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":32.9105,"mmsi_bench":29.2,"mindcube_tiny":48.8462,"viewspatial":41.6842,"site":39.6739,"blink":63.8085,"3dsrbench":53.6164,"embspatial":72.3077,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":43.0421,"object_abs_distance":15.6595,"object_counting":40.7965,"object_rel_direction_accuracy":43.3299,"object_rel_distance_accuracy":40.9859,"object_size_estimation":14.2078,"room_size_estimation":33.8194,"route_planning_accuracy":31.4433},"mmsi_bench":{"attr_appr_accuracy":24.2424,"attr_meas_accuracy":54.6875,"motion_cam_accuracy":17.5676,"motion_obj_accuracy":25,"msr_accuracy":30.8081,"pos_cam_cam_accuracy":30.1075,"pos_cam_obj_accuracy":25.5814,"pos_cam_reg_accuracy":30.1205,"pos_obj_obj_accuracy":20.2128,"pos_obj_reg_accuracy":37.6471,"pos_reg_reg_accuracy":27.1605},"mindcube_tiny":{"among_accuracy":40.678,"around_accuracy":50.4,"rotation_accuracy":71},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":24.498,"camera_perspective_relative_direction_accuracy":52.6791,"person_perspective_object_view_orientation_accuracy":55.0201,"person_perspective_relative_direction_accuracy":40.4988,"person_perspective_scene_simulation_relative_direction_accuracy":28.4163},"site":{"3d_information_understanding_caa":26.3974,"counting_and_existence_caa":46.3275,"movement_prediction_and_navigation_caa":19.8756,"multiview_and_crossimage_reasoning_caa":15.8065,"object_localization_and_positioning_caa":67.9887,"spatial_relationship_reasoning_caa":59.9451},"blink":{"art_style":71.7949,"counting":70.8333,"forensic_detection":52.2727,"functional_correspondence":56.9231,"iq_test":31.3333,"jigsaw":60.6667,"multi_view_reasoning":46.6165,"object_localization":68.8525,"relative_depth":88.7097,"relative_reflectance":31.3433,"semantic_correspondence":57.554,"spatial_relation":90.2098,"visual_correspondence":84.3023,"visual_similarity":82.2222},"3dsrbench":{"height_higher":51.0145,"location_above":65.896,"location_closer_to_camera":73.4513,"location_next_to":73.4513,"multi_object_closer_to":58.5714,"multi_object_facing":62.1387,"multi_object_parallel":51.6224,"multi_object_same_direction":37.5,"multi_object_viewpoint_towards_object":14.2857,"orientation_in_front_of":62.2093,"orientation_on_the_left":33.2378,"orientation_viewpoint":31.1953},"embspatial":{"ai2thor_accuracy":70.7829,"mp3d_accuracy":71.8568,"scannet_accuracy":74.3333}}},{"name":"Qwen3.5-9B","displayName":"Qwen3.5-9B","link":"https://huggingface.co/Qwen/Qwen3.5-9B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":54.2514,"vsi_bench_128frames":55.6795,"mmsi_bench":38.7,"mindcube_tiny":57.5962,"viewspatial":48.1968,"site":42.3382,"blink":67.596,"3dsrbench":56.7772,"embspatial":81.5385,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":67.3139,"object_abs_distance":37.8897,"object_counting":48.6195,"object_rel_direction_accuracy":51.8224,"object_rel_distance_accuracy":63.3803,"object_size_estimation":66.2644,"room_size_estimation":55.9375,"route_planning_accuracy":42.7835},"vsi_bench_128frames":{"obj_appearance_order_accuracy":70.712,"object_abs_distance":37.458,"object_counting":53.8761,"object_rel_direction_accuracy":55.1292,"object_rel_distance_accuracy":63.5211,"object_size_estimation":66.0965,"room_size_estimation":51.7361,"route_planning_accuracy":46.9072},"mmsi_bench":{"attr_appr_accuracy":25.7576,"attr_meas_accuracy":50,"motion_cam_accuracy":33.7838,"motion_obj_accuracy":28.9474,"msr_accuracy":35.8586,"pos_cam_cam_accuracy":35.4839,"pos_cam_obj_accuracy":39.5349,"pos_cam_reg_accuracy":57.8313,"pos_obj_obj_accuracy":37.234,"pos_obj_reg_accuracy":41.1765,"pos_reg_reg_accuracy":43.2099},"mindcube_tiny":{"among_accuracy":42.5424,"around_accuracy":64.4,"rotation_accuracy":93.5},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":34.3373,"camera_perspective_relative_direction_accuracy":58.432,"person_perspective_object_view_orientation_accuracy":48.6948,"person_perspective_relative_direction_accuracy":57.4822,"person_perspective_scene_simulation_relative_direction_accuracy":36.7421},"site":{"3d_information_understanding_caa":39.9429,"counting_and_existence_caa":54.1682,"movement_prediction_and_navigation_caa":32.5661,"multiview_and_crossimage_reasoning_caa":8.2707,"object_localization_and_positioning_caa":61.1898,"spatial_relationship_reasoning_caa":60.2919},"blink":{"art_style":82.0513,"counting":72.5,"forensic_detection":71.2121,"functional_correspondence":67.6923,"iq_test":34,"jigsaw":77.3333,"multi_view_reasoning":21.0526,"object_localization":70.4918,"relative_depth":85.4839,"relative_reflectance":34.3284,"semantic_correspondence":65.4676,"spatial_relation":87.4126,"visual_correspondence":91.8605,"visual_similarity":83.7037},"3dsrbench":{"height_higher":51.7391,"location_above":60.6936,"location_closer_to_camera":80.9735,"location_next_to":65.7817,"multi_object_closer_to":64,"multi_object_facing":63.8728,"multi_object_parallel":48.6726,"multi_object_same_direction":48.8372,"multi_object_viewpoint_towards_object":21.5743,"orientation_in_front_of":74.7093,"orientation_on_the_left":41.8338,"orientation_viewpoint":36.1516},"embspatial":{"ai2thor_accuracy":79.9839,"mp3d_accuracy":81.6819,"scannet_accuracy":83}}},{"name":"Qwen3-VL-8B-Thinking","displayName":"Qwen3-VL-8B-Thinking","link":"https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":54.3371,"vsi_bench_128frames":56.6118,"mmsi_bench":28.6,"mindcube_tiny":43.1731,"viewspatial":47.2514,"site":45.2143,"blink":63.5981,"3dsrbench":54.489,"embspatial":80.0275,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":70.712,"object_abs_distance":42.4221,"object_counting":48.5487,"object_rel_direction_accuracy":49.761,"object_rel_distance_accuracy":60.2817,"object_size_estimation":69.8216,"room_size_estimation":55.5208,"route_planning_accuracy":37.6289},"vsi_bench_128frames":{"obj_appearance_order_accuracy":69.2557,"object_abs_distance":43.0336,"object_counting":54.9558,"object_rel_direction_accuracy":51.9454,"object_rel_distance_accuracy":62.9577,"object_size_estimation":71.1228,"room_size_estimation":56.8403,"route_planning_accuracy":42.7835},"mmsi_bench":{"attr_appr_accuracy":16.6667,"attr_meas_accuracy":50,"motion_cam_accuracy":17.5676,"motion_obj_accuracy":23.6842,"msr_accuracy":27.2727,"pos_cam_cam_accuracy":31.1828,"pos_cam_obj_accuracy":29.0698,"pos_cam_reg_accuracy":30.1205,"pos_obj_obj_accuracy":26.5957,"pos_obj_reg_accuracy":32.9412,"pos_reg_reg_accuracy":32.0988},"mindcube_tiny":{"among_accuracy":32.0339,"around_accuracy":50.4,"rotation_accuracy":67},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":32.5301,"camera_perspective_relative_direction_accuracy":57.9244,"person_perspective_object_view_orientation_accuracy":59.6386,"person_perspective_relative_direction_accuracy":45.8432,"person_perspective_scene_simulation_relative_direction_accuracy":33.3032},"site":{"3d_information_understanding_caa":48.1028,"counting_and_existence_caa":59.3415,"movement_prediction_and_navigation_caa":34.8056,"multiview_and_crossimage_reasoning_caa":12.4284,"object_localization_and_positioning_caa":58.7819,"spatial_relationship_reasoning_caa":60.2919},"blink":{"art_style":77.7778,"counting":71.6667,"forensic_detection":62.1212,"functional_correspondence":46.1538,"iq_test":27.3333,"jigsaw":62.6667,"multi_view_reasoning":40.6015,"object_localization":65.5738,"relative_depth":81.4516,"relative_reflectance":36.5672,"semantic_correspondence":62.5899,"spatial_relation":87.4126,"visual_correspondence":84.3023,"visual_similarity":84.4444},"3dsrbench":{"height_higher":54.4928,"location_above":65.4624,"location_closer_to_camera":81.4159,"location_next_to":63.1268,"multi_object_closer_to":65.1429,"multi_object_facing":62.7168,"multi_object_parallel":44.2478,"multi_object_same_direction":42.4419,"multi_object_viewpoint_towards_object":16.6181,"orientation_in_front_of":61.3372,"orientation_on_the_left":32.6648,"orientation_viewpoint":26.8222},"embspatial":{"ai2thor_accuracy":76.8362,"mp3d_accuracy":82.0983,"scannet_accuracy":81.25}}},{"name":"Qwen3-VL-30B-A3B-Thinking","displayName":"Qwen3-VL-30B-A3B-Thinking","link":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":50.5574,"vsi_bench_128frames":51.5675,"mmsi_bench":29.4,"mindcube_tiny":40.8654,"viewspatial":47.3739,"site":47.2257,"blink":63.8611,"3dsrbench":55.5556,"embspatial":80.3846,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":62.4595,"object_abs_distance":36.4269,"object_counting":50.9381,"object_rel_direction_accuracy":49.2509,"object_rel_distance_accuracy":53.3803,"object_size_estimation":69.8636,"room_size_estimation":47.6042,"route_planning_accuracy":34.5361},"vsi_bench_128frames":{"obj_appearance_order_accuracy":63.2686,"object_abs_distance":35.5156,"object_counting":52.2301,"object_rel_direction_accuracy":50.8237,"object_rel_distance_accuracy":53.5211,"object_size_estimation":71.574,"room_size_estimation":50.5556,"route_planning_accuracy":35.0515},"mmsi_bench":{"attr_appr_accuracy":19.697,"attr_meas_accuracy":40.625,"motion_cam_accuracy":18.9189,"motion_obj_accuracy":27.6316,"msr_accuracy":31.3131,"pos_cam_cam_accuracy":23.6559,"pos_cam_obj_accuracy":31.3953,"pos_cam_reg_accuracy":22.8916,"pos_obj_obj_accuracy":31.9149,"pos_obj_reg_accuracy":36.4706,"pos_reg_reg_accuracy":35.8025},"mindcube_tiny":{"among_accuracy":33.5593,"around_accuracy":45.2,"rotation_accuracy":57},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":34.739,"camera_perspective_relative_direction_accuracy":58.3756,"person_perspective_object_view_orientation_accuracy":61.245,"person_perspective_relative_direction_accuracy":45.1306,"person_perspective_scene_simulation_relative_direction_accuracy":30.3167},"site":{"3d_information_understanding_caa":40.5957,"counting_and_existence_caa":61.3623,"movement_prediction_and_navigation_caa":38.1649,"multiview_and_crossimage_reasoning_caa":15.6333,"object_localization_and_positioning_caa":63.5977,"spatial_relationship_reasoning_caa":63.4997},"blink":{"art_style":71.7949,"counting":74.1667,"forensic_detection":69.697,"functional_correspondence":52.3077,"iq_test":36.6667,"jigsaw":56,"multi_view_reasoning":45.1128,"object_localization":58.1967,"relative_depth":81.4516,"relative_reflectance":32.8358,"semantic_correspondence":61.1511,"spatial_relation":85.3147,"visual_correspondence":86.6279,"visual_similarity":81.4815},"3dsrbench":{"height_higher":55.5072,"location_above":66.474,"location_closer_to_camera":79.7935,"location_next_to":67.8466,"multi_object_closer_to":67.7143,"multi_object_facing":58.3815,"multi_object_parallel":45.7227,"multi_object_same_direction":42.7326,"multi_object_viewpoint_towards_object":20.9913,"orientation_in_front_of":61.6279,"orientation_on_the_left":33.8109,"orientation_viewpoint":31.4869},"embspatial":{"ai2thor_accuracy":78.0468,"mp3d_accuracy":82.015,"scannet_accuracy":81.1667}}},{"name":"qwen3_5_vl_35b_a3b","displayName":"Qwen3.5-VL-35B-A3B","link":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":58.1005,"vsi_bench_128frames":61.1337,"mmsi_bench":41.9,"mindcube_tiny":63.4615,"viewspatial":50.7878,"site":61.3941,"blink":70.4892,"3dsrbench":59.8216,"embspatial":83.5989,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":71.3592,"object_abs_distance":41.1271,"object_counting":53.469,"object_rel_direction_accuracy":52.7077,"object_rel_distance_accuracy":66.338,"object_size_estimation":69.979,"room_size_estimation":56.2153,"route_planning_accuracy":53.6082},"vsi_bench_128frames":{"obj_appearance_order_accuracy":79.6117,"object_abs_distance":42.8417,"object_counting":58.0531,"object_rel_direction_accuracy":58.1118,"object_rel_distance_accuracy":68.8732,"object_size_estimation":69.5908,"room_size_estimation":59.4097,"route_planning_accuracy":52.5773},"mmsi_bench":{"attr_appr_accuracy":33.3333,"attr_meas_accuracy":54.6875,"motion_cam_accuracy":37.8378,"motion_obj_accuracy":36.8421,"msr_accuracy":37.8788,"pos_cam_cam_accuracy":45.1613,"pos_cam_obj_accuracy":44.186,"pos_cam_reg_accuracy":60.241,"pos_obj_obj_accuracy":41.4894,"pos_obj_reg_accuracy":41.1765,"pos_reg_reg_accuracy":33.3333},"mindcube_tiny":{"among_accuracy":49.1525,"around_accuracy":72,"rotation_accuracy":95},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":36.747,"camera_perspective_relative_direction_accuracy":60.6317,"person_perspective_object_view_orientation_accuracy":48.3936,"person_perspective_relative_direction_accuracy":61.9952,"person_perspective_scene_simulation_relative_direction_accuracy":41.267},"site":{"3d_information_understanding_caa":62.4643,"counting_and_existence_caa":64.9997,"movement_prediction_and_navigation_caa":53.0949,"multiview_and_crossimage_reasoning_caa":43.5245,"object_localization_and_positioning_caa":74.3626,"spatial_relationship_reasoning_caa":72.6898},"blink":{"art_style":78.6325,"counting":77.5,"forensic_detection":70.4545,"functional_correspondence":70,"iq_test":38,"jigsaw":74.6667,"multi_view_reasoning":32.3308,"object_localization":77.0492,"relative_depth":87.9032,"relative_reflectance":29.8507,"semantic_correspondence":72.6619,"spatial_relation":91.6084,"visual_correspondence":96.5116,"visual_similarity":87.4074},"3dsrbench":{"height_higher":56.2319,"location_above":64.7399,"location_closer_to_camera":82.4484,"location_next_to":65.7817,"multi_object_closer_to":61.4286,"multi_object_facing":65.6069,"multi_object_parallel":53.6873,"multi_object_same_direction":50.8721,"multi_object_viewpoint_towards_object":22.449,"orientation_in_front_of":78.4884,"orientation_on_the_left":53.5817,"orientation_viewpoint":39.0671},"embspatial":{"ai2thor_accuracy":83.1316,"mp3d_accuracy":83.597,"scannet_accuracy":84.0833}}},{"name":"sensenova-u1-a3b-mot","displayName":"SenseNova-U1-A3B-MoT","link":"https://huggingface.co/sensenova/SenseNova-U1-A3B-MoT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":56.9036,"vsi_bench_128frames":56.9306,"mmsi_bench":39,"mindcube_tiny":70.8654,"viewspatial":58.5259,"site":47.6139,"blink":59.8106,"3dsrbench":62.963,"embspatial":81.4011,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":59.8706,"object_abs_distance":44.3405,"object_counting":62.9027,"object_rel_direction_accuracy":62.0949,"object_rel_distance_accuracy":56.338,"object_size_estimation":71.4795,"room_size_estimation":52.3264,"route_planning_accuracy":45.8763},"vsi_bench_128frames":{"obj_appearance_order_accuracy":62.4595,"object_abs_distance":45.2758,"object_counting":63.4159,"object_rel_direction_accuracy":61.2832,"object_rel_distance_accuracy":53.3803,"object_size_estimation":69.2235,"room_size_estimation":56.0764,"route_planning_accuracy":44.3299},"mmsi_bench":{"attr_appr_accuracy":37.8788,"attr_meas_accuracy":40.625,"motion_cam_accuracy":28.3784,"motion_obj_accuracy":30.2632,"msr_accuracy":24.2424,"pos_cam_cam_accuracy":41.9355,"pos_cam_obj_accuracy":61.6279,"pos_cam_reg_accuracy":60.241,"pos_obj_obj_accuracy":44.6809,"pos_obj_reg_accuracy":34.1176,"pos_reg_reg_accuracy":41.9753},"mindcube_tiny":{"among_accuracy":64.4068,"around_accuracy":74.8,"rotation_accuracy":85},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":36.6466,"camera_perspective_relative_direction_accuracy":72.5324,"person_perspective_object_view_orientation_accuracy":56.2249,"person_perspective_relative_direction_accuracy":49.4062,"person_perspective_scene_simulation_relative_direction_accuracy":64.7964},"site":{"3d_information_understanding_caa":45.002,"counting_and_existence_caa":48.3483,"movement_prediction_and_navigation_caa":32.6905,"multiview_and_crossimage_reasoning_caa":35.1225,"object_localization_and_positioning_caa":61.4731,"spatial_relationship_reasoning_caa":62.6328},"blink":{"art_style":70.9402,"counting":70,"forensic_detection":23.4848,"functional_correspondence":45.3846,"iq_test":12.6667,"jigsaw":72,"multi_view_reasoning":30.8271,"object_localization":61.4754,"relative_depth":87.0968,"relative_reflectance":34.3284,"semantic_correspondence":60.4317,"spatial_relation":90.2098,"visual_correspondence":88.9535,"visual_similarity":86.6667},"3dsrbench":{"height_higher":58.4058,"location_above":57.3699,"location_closer_to_camera":84.6608,"location_next_to":70.5015,"multi_object_closer_to":69.7143,"multi_object_facing":75.4335,"multi_object_parallel":55.7522,"multi_object_same_direction":59.3023,"multi_object_viewpoint_towards_object":36.1516,"orientation_in_front_of":75.2907,"orientation_on_the_left":53.5817,"orientation_viewpoint":48.3965},"embspatial":{"ai2thor_accuracy":77.0783,"mp3d_accuracy":81.7652,"scannet_accuracy":85.5}}},{"name":"sensenova_si_1.5_internvl3_8b","displayName":"SenseNova-SI-1.5-InternVL3-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.5-InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":67.27,"mmsi_bench":38.3,"mindcube_tiny":92.12,"viewspatial":59,"site":47.5,"blink":69.49,"3dsrbench":61.12,"embspatial":80.36,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":77.99,"object_abs_distance":53.9,"object_counting":70.51,"object_rel_direction_accuracy":82.19,"object_rel_distance_accuracy":69.58,"object_size_estimation":71.79,"room_size_estimation":67.33,"route_planning_accuracy":44.85},"mmsi_bench":{"attr_appr_accuracy":31.82,"attr_meas_accuracy":37.5,"motion_cam_accuracy":35.14,"motion_obj_accuracy":30.26,"msr_accuracy":23.23,"pos_cam_cam_accuracy":37.63,"pos_cam_obj_accuracy":61.63,"pos_cam_reg_accuracy":61.45,"pos_obj_obj_accuracy":40.43,"pos_obj_reg_accuracy":41.18,"pos_reg_reg_accuracy":38.27},"mindcube_tiny":{"among_accuracy":93.56,"around_accuracy":90.8,"rotation_accuracy":89.5},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":35.14,"camera_perspective_relative_direction_accuracy":74.11,"person_perspective_object_view_orientation_accuracy":47.69,"person_perspective_relative_direction_accuracy":55.11,"person_perspective_scene_simulation_relative_direction_accuracy":69.41},"site":{"3d_information_understanding_caa":42.39,"counting_and_existence_caa":53.84,"movement_prediction_and_navigation_caa":30.7,"multiview_and_crossimage_reasoning_caa":40.84,"object_localization_and_positioning_caa":51.7,"spatial_relationship_reasoning_caa":57.43},"blink":{"art_style":81.2,"counting":65,"forensic_detection":28.79,"functional_correspondence":44.62,"iq_test":24,"jigsaw":84.67,"multi_view_reasoning":96.24,"object_localization":61.48,"relative_depth":91.94,"relative_reflectance":32.09,"semantic_correspondence":82.01,"spatial_relation":88.81,"visual_correspondence":96.51,"visual_similarity":90.37},"3dsrbench":{"height_higher":53.19,"location_above":50,"location_closer_to_camera":84.66,"location_next_to":67.26,"multi_object_closer_to":70.86,"multi_object_facing":78.32,"multi_object_parallel":51.33,"multi_object_same_direction":53.2,"multi_object_viewpoint_towards_object":43.44,"orientation_in_front_of":70.35,"orientation_on_the_left":70.77,"orientation_viewpoint":35.86},"embspatial":{"ai2thor_accuracy":75.46,"mp3d_accuracy":81.35,"scannet_accuracy":84.42}}},{"name":"sensenova_si_1.4_internvl3_8b","displayName":"SenseNova-SI-1.4-InternVL3-8B","link":"https://huggingface.co/sensenova/SenseNova-SI-1.4-InternVL3-8B","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":66.61,"mmsi_bench":40.1,"mindcube_tiny":88.85,"viewspatial":55.67,"site":47.9,"blink":68.12,"3dsrbench":62.19,"embspatial":81.7,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":78.96,"object_abs_distance":51.65,"object_counting":71.22,"object_rel_direction_accuracy":80.35,"object_rel_distance_accuracy":68.17,"object_size_estimation":75.22,"room_size_estimation":64.03,"route_planning_accuracy":43.3},"mmsi_bench":{"attr_appr_accuracy":31.82,"attr_meas_accuracy":37.5,"motion_cam_accuracy":32.43,"motion_obj_accuracy":35.53,"msr_accuracy":25.76,"pos_cam_cam_accuracy":39.78,"pos_cam_obj_accuracy":61.63,"pos_cam_reg_accuracy":69.88,"pos_obj_obj_accuracy":44.68,"pos_obj_reg_accuracy":43.53,"pos_reg_reg_accuracy":33.33},"mindcube_tiny":{"among_accuracy":89.32,"around_accuracy":87.6,"rotation_accuracy":89},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":31.83,"camera_perspective_relative_direction_accuracy":72.87,"person_perspective_object_view_orientation_accuracy":37.05,"person_perspective_relative_direction_accuracy":49.52,"person_perspective_scene_simulation_relative_direction_accuracy":71.04},"site":{"3d_information_understanding_caa":45.98,"counting_and_existence_caa":56.43,"movement_prediction_and_navigation_caa":36.55,"multiview_and_crossimage_reasoning_caa":34.08,"object_localization_and_positioning_caa":49.01,"spatial_relationship_reasoning_caa":59.16},"blink":{"art_style":74.36,"counting":61.67,"forensic_detection":27.27,"functional_correspondence":50.77,"iq_test":24.67,"jigsaw":82.67,"multi_view_reasoning":90.98,"object_localization":54.92,"relative_depth":94.35,"relative_reflectance":35.82,"semantic_correspondence":76.98,"spatial_relation":88.11,"visual_correspondence":96.51,"visual_similarity":88.15},"3dsrbench":{"height_higher":53.91,"location_above":55.78,"location_closer_to_camera":87.46,"location_next_to":63.72,"multi_object_closer_to":75.14,"multi_object_facing":81.21,"multi_object_parallel":54.28,"multi_object_same_direction":53.49,"multi_object_viewpoint_towards_object":43.15,"orientation_in_front_of":67.15,"orientation_on_the_left":69.34,"orientation_viewpoint":31.2},"embspatial":{"ai2thor_accuracy":77.97,"mp3d_accuracy":83.35,"scannet_accuracy":83.92}}},{"name":"neoov_9b_si","displayName":"NEO-ov-9B-SFT","link":"https://huggingface.co/Paranioar/NEO1_5-9B-SFT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":64.79,"mmsi_bench":41.3,"mindcube_tiny":90,"viewspatial":55.16,"site":53.97,"blink":62.81,"3dsrbench":61.24,"embspatial":77.77,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":77.67,"object_abs_distance":49.27,"object_counting":70.97,"object_rel_direction_accuracy":66.47,"object_rel_distance_accuracy":64.23,"object_size_estimation":75.47,"room_size_estimation":70.42,"route_planning_accuracy":43.81},"mmsi_bench":{"attr_appr_accuracy":34.85,"attr_meas_accuracy":50,"motion_cam_accuracy":40.54,"motion_obj_accuracy":27.63,"msr_accuracy":27.78,"pos_cam_cam_accuracy":44.09,"pos_cam_obj_accuracy":59.3,"pos_cam_reg_accuracy":63.86,"pos_obj_obj_accuracy":39.36,"pos_obj_reg_accuracy":45.88,"pos_reg_reg_accuracy":38.27},"mindcube_tiny":{"among_accuracy":89.32,"around_accuracy":89.2,"rotation_accuracy":93},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":35.74,"camera_perspective_relative_direction_accuracy":68.81,"person_perspective_object_view_orientation_accuracy":44.08,"person_perspective_relative_direction_accuracy":45.84,"person_perspective_scene_simulation_relative_direction_accuracy":67.87},"site":{"3d_information_understanding_caa":52.84,"counting_and_existence_caa":61.6,"movement_prediction_and_navigation_caa":51.48,"multiview_and_crossimage_reasoning_caa":27.33,"object_localization_and_positioning_caa":67.28,"spatial_relationship_reasoning_caa":66.62},"blink":{"art_style":79.49,"counting":79.17,"forensic_detection":50,"functional_correspondence":53.85,"iq_test":24,"jigsaw":76.67,"multi_view_reasoning":10.53,"object_localization":65.57,"relative_depth":85.48,"relative_reflectance":39.55,"semantic_correspondence":48.2,"spatial_relation":88.81,"visual_correspondence":89.53,"visual_similarity":87.41},"3dsrbench":{"height_higher":51.3,"location_above":64.16,"location_closer_to_camera":82.01,"location_next_to":63.42,"multi_object_closer_to":68.57,"multi_object_facing":77.46,"multi_object_parallel":51.92,"multi_object_same_direction":50.87,"multi_object_viewpoint_towards_object":37.03,"orientation_in_front_of":70.64,"orientation_on_the_left":62.46,"orientation_viewpoint":41.4},"embspatial":{"ai2thor_accuracy":72.16,"mp3d_accuracy":78.18,"scannet_accuracy":83.17}}},{"name":"neoov_2b_si","displayName":"NEO-ov-2B-SFT","link":"https://huggingface.co/Paranioar/NEO1_5-2B-SFT","backend":"vlmevalkit","type":"instruction","precision":"bfloat16","scores":{"vsi_bench":58.37,"mmsi_bench":33.6,"mindcube_tiny":77.21,"viewspatial":52.8,"site":42.99,"blink":53.81,"3dsrbench":52.45,"embspatial":63.82,"mmsi_video_bench":null,"omnispatial_(manual_cot)":null,"spar_bench":null,"vsi_debiased":null},"subScores":{"vsi_bench":{"obj_appearance_order_accuracy":64.08,"object_abs_distance":43.62,"object_counting":68.74,"object_rel_direction_accuracy":57.36,"object_rel_distance_accuracy":58.45,"object_size_estimation":73.31,"room_size_estimation":60.14,"route_planning_accuracy":41.24},"mmsi_bench":{"attr_appr_accuracy":24.24,"attr_meas_accuracy":31.25,"motion_cam_accuracy":54.05,"motion_obj_accuracy":34.21,"msr_accuracy":23.23,"pos_cam_cam_accuracy":37.63,"pos_cam_obj_accuracy":40.7,"pos_cam_reg_accuracy":36.14,"pos_obj_obj_accuracy":43.62,"pos_obj_reg_accuracy":31.76,"pos_reg_reg_accuracy":24.69},"mindcube_tiny":{"among_accuracy":72.71,"around_accuracy":86.8,"rotation_accuracy":78.5},"viewspatial":{"camera_perspective_object_view_orientation_accuracy":38.05,"camera_perspective_relative_direction_accuracy":63.51,"person_perspective_object_view_orientation_accuracy":50.2,"person_perspective_relative_direction_accuracy":39.19,"person_perspective_scene_simulation_relative_direction_accuracy":61.63},"site":{"3d_information_understanding_caa":26.89,"counting_and_existence_caa":52.79,"movement_prediction_and_navigation_caa":40.4,"multiview_and_crossimage_reasoning_caa":19.88,"object_localization_and_positioning_caa":52.69,"spatial_relationship_reasoning_caa":60.03},"blink":{"art_style":66.67,"counting":69.17,"forensic_detection":40.91,"functional_correspondence":31.54,"iq_test":21.33,"jigsaw":63.33,"multi_view_reasoning":0,"object_localization":56.56,"relative_depth":79.84,"relative_reflectance":34.33,"semantic_correspondence":44.6,"spatial_relation":81.12,"visual_correspondence":81.98,"visual_similarity":79.26},"3dsrbench":{"height_higher":55.22,"location_above":56.21,"location_closer_to_camera":74.04,"location_next_to":52.51,"multi_object_closer_to":61.14,"multi_object_facing":64.74,"multi_object_parallel":44.54,"multi_object_same_direction":52.03,"multi_object_viewpoint_towards_object":20.99,"orientation_in_front_of":51.74,"orientation_on_the_left":36.68,"orientation_viewpoint":31.78},"embspatial":{"ai2thor_accuracy":62.55,"mp3d_accuracy":63.36,"scannet_accuracy":65.58}}}],"lastUpdated":"2026-07-01T17:34:33Z","capabilityMap":{"vsi_bench":{"object_counting":["cr"],"object_abs_distance":["mm"],"object_size_estimation":["mm"],"room_size_estimation":["mm"],"object_rel_distance_accuracy":["sr","mm"],"object_rel_direction_accuracy":["pt"],"route_planning_accuracy":["cr"],"obj_appearance_order_accuracy":["cr"]},"vsi_debiased":{"object_counting":["cr"],"object_abs_distance":["mm"],"object_size_estimation":["mm"],"room_size_estimation":["mm"],"object_rel_distance_accuracy":["sr","mm"],"object_rel_direction_accuracy":["pt"],"route_planning_accuracy":["cr"],"obj_appearance_order_accuracy":["cr"]},"site":{"counting_and_existence_caa":[],"object_localization_and_positioning_caa":[],"3d_information_understanding_caa":["mm","sr"],"multiview_and_crossimage_reasoning_caa":["pt"],"spatial_relationship_reasoning_caa":["sr"],"movement_prediction_and_navigation_caa":["cr"]},"mmsi_bench":{"pos_cam_cam_accuracy":["pt"],"pos_obj_obj_accuracy":["pt"],"pos_reg_reg_accuracy":["pt"],"pos_cam_obj_accuracy":["pt"],"pos_obj_reg_accuracy":["pt"],"pos_cam_reg_accuracy":["pt"],"attr_meas_accuracy":["mm"],"attr_appr_accuracy":["mr"],"motion_cam_accuracy":["pt"],"motion_obj_accuracy":["pt"],"msr_accuracy":["cr"]},"omnispatial_(manual_cot)":{"manipulation_accuracy":[],"motion_analysis_accuracy":["mm","cr"],"traffic_analysis_accuracy":["cr"],"localization_accuracy":[],"geospatial_strategy_accuracy":[],"pattern_recognition_accuracy":["cr"],"geometric_reasoning_accuracy":["cr"],"egocentric_accuracy":[],"allocentric_accuracy":["pt"],"hypothetical_accuracy":["pt"]},"mindcube_tiny":{"rotation_accuracy":["pt"],"among_accuracy":["pt"],"around_accuracy":["pt"]},"embspatial":{"mp3d_accuracy":["sr"],"ai2thor_accuracy":["sr"],"scannet_accuracy":["sr"]},"3dsrbench":{"height_higher":["sr"],"location_above":["sr"],"location_closer_to_camera":["sr"],"location_next_to":["sr"],"multi_object_closer_to":["pt","sr"],"multi_object_facing":["pt","sr"],"multi_object_parallel":["pt","sr"],"multi_object_same_direction":["pt","sr"],"multi_object_viewpoint_towards_object":["pt","sr"],"orientation_in_front_of":["pt"],"orientation_on_the_left":["pt"],"orientation_viewpoint":["pt"]},"blink":{"art_style":[],"counting":[],"forensic_detection":[],"functional_correspondence":[],"iq_test":["cr"],"jigsaw":[],"multi_view_reasoning":["pt"],"object_localization":[],"relative_depth":["sr"],"relative_reflectance":[],"semantic_correspondence":[],"spatial_relation":["sr"],"visual_correspondence":["pt"],"visual_similarity":[]},"mmsi_video_bench":{"instance_scene_attribute_accuracy":["cr"],"instance_instance_spatial_relationship_accuracy":["pt"],"instance_scene_spatial_relationship_accuracy":["cr"],"scene_scene_spatial_relationship_accuracy":["cr"],"camera_instance_spatial_relationship_accuracy":[],"camera_scene_spatial_relationship_accuracy":["pt"],"camera_motion_accuracy":["cr"],"instance_motion_accuracy":["cr"],"interactive_motion_accuracy":[],"memoery_update_accuracy":[],"multi_view_integration_accuracy":["cr"],"planning_accuracy":["cr"],"prediction_accuracy":["cr"]},"spar_bench":{"depth_prediction_oc":["mm"],"depth_prediction_oc_mv":["mm"],"depth_prediction_oo":["mm","sr"],"depth_prediction_oo_mv":["mm","sr"],"distance_prediction_oc":["mm"],"distance_prediction_oc_mv":["mm"],"distance_prediction_oo":["mm","sr"],"distance_prediction_oo_mv":["sr"],"position_matching_accuracy":["pt"],"camera_motion_infer_accuracy":["pt"],"view_change_infer_vci_metric":["pt"],"distance_infer_center_oo_accuracy":["sr"],"distance_infer_center_oo_mv_accuracy":["mm","sr"],"obj_spatial_relation_oc_mv_accuracy":["pt"],"obj_spatial_relation_oo_accuracy":["sr"],"obj_spatial_relation_oo_mv_accuracy":["sr"],"spatial_imagination_oc_accuracy":["pt"],"spatial_imagination_oc_mv_accuracy":["pt"],"spatial_imagination_oo_accuracy":["pt"],"spatial_imagination_oo_mv_accuracy":["pt"]},"viewspatial":{"camera_perspective_relative_direction_accuracy":["sr"],"person_perspective_scene_simulation_relative_direction_accuracy":["pt"],"camera_perspective_object_view_orientation_accuracy":["pt"],"person_perspective_object_view_orientation_accuracy":["pt"],"person_perspective_relative_direction_accuracy":["pt"]}}}