{ "updatedAt": "2026-09-15T12:47:11.769434+00:00", "parserVersion": "icra27-dual-v5-class-aware-f1-selected-view", "definition": "Independent paired semantic and evidence co-success; Overall = H(H(Position, Action-Observation), Behavior-Visibility).", "correlationPolicy": "Unrounded, equal model weights, retain zeros, pairwise exclude missing; average ranks for ties. Descriptive, not causal.", "image": [ { "label": "Claude Opus 4.8", "group": "proprietary", "self_where_acc": 39.35546875, "self_where_bbox50": 11.42578125, "self_where_iou": 23.511914454081666, "self_what_acc": 35.9375, "self_what_bbox50": 14.2578125, "self_what_iou": 25.3603463465568, "env_where_acc": 54.1015625, "env_where_bbox50": 10.44921875, "env_where_iou": 23.708533618316345, "env_how_acc": 51.85546875, "env_how_bbox50": 8.0078125, "env_how_iou": 21.709721661825846, "image_dual_sem": 19.529296875, "image_dual_evi": 2.4892769607843137 }, { "label": "Claude Opus 4.7", "group": "proprietary", "self_where_acc": 39.2578125, "self_where_bbox50": 8.203125, "self_where_iou": 20.090918316127723, "self_what_acc": 37.20703125, "self_what_bbox50": 7.03125, "self_what_iou": 18.121905878917058, "env_where_acc": 49.70703125, "env_where_bbox50": 7.12890625, "env_where_iou": 18.616219025370047, "env_how_acc": 39.0625, "env_how_bbox50": 7.91015625, "env_how_iou": 17.991440993105474, "image_dual_sem": 16.695290050287355, "image_dual_evi": 1.065340909090909 }, { "label": "Claude Opus 4.6", "group": "proprietary", "self_where_acc": 38.0859375, "self_where_bbox50": 2.1484375, "self_where_iou": 15.634666545460805, "self_what_acc": 32.421875, "self_what_bbox50": 2.83203125, "self_what_iou": 18.725613134041826, "env_where_acc": 62.01171875, "env_where_bbox50": 8.59375, "env_where_iou": 19.683677121962404, "env_how_acc": 58.88671875, "env_how_bbox50": 9.1796875, "env_how_iou": 20.05505169886616, "image_dual_sem": 20.53683298938679, "image_dual_evi": 0 }, { "label": "Claude Sonnet 4.6", "group": "proprietary", "self_where_acc": 37.6953125, "self_where_bbox50": 4.8828125, "self_where_iou": 18.233124906119773, "self_what_acc": 23.6328125, "self_what_bbox50": 3.61328125, "self_what_iou": 15.079294696380085, "env_where_acc": 48.53515625, "env_where_bbox50": 9.5703125, "env_where_iou": 20.21838951660152, "env_how_acc": 61.03515625, "env_how_bbox50": 8.59375, "env_how_iou": 19.871907975809922, "image_dual_sem": 15.915572277607362, "image_dual_evi": 0.146484375 }, { "label": "Gemini 3.8 Flash", "group": "proprietary", "self_where_acc": 60.05859375, "self_where_bbox50": 66.69921875, "self_where_iou": 57.61157830326798, "self_what_acc": 74.90234375, "self_what_bbox50": 73.828125, "self_what_iou": 62.5421495506407, "env_where_acc": 61.9140625, "env_where_bbox50": 40.8203125, "env_where_iou": 39.019384438736424, "env_how_acc": 69.53125, "env_how_bbox50": 42.28515625, "env_how_iou": 39.28306985689471, "image_dual_sem": 44.39476152197213, "image_dual_evi": 34.27484685724432 }, { "label": "Gemini 3.1 Pro Preview", "group": "proprietary", "self_where_acc": 40.91796875, "self_where_bbox50": 58.7890625, "self_where_iou": 50.469465993067416, "self_what_acc": 58.7890625, "self_what_bbox50": 59.86328125, "self_what_iou": 52.2916979487563, "env_where_acc": 63.671875, "env_where_bbox50": 37.5, "env_where_iou": 36.77649826967787, "env_how_acc": 47.16796875, "env_how_bbox50": 37.109375, "env_how_iou": 36.43367641668675, "image_dual_sem": 27.050428700361014, "image_dual_evi": 30.113578808752028 }, { "label": "Gemini 3.1 Flash Lite", "group": "proprietary", "self_where_acc": 33.69140625, "self_where_bbox50": 48.14453125, "self_where_iou": 45.66776570824918, "self_what_acc": 30.078125, "self_what_bbox50": 47.94921875, "self_what_iou": 46.044338778460585, "env_where_acc": 47.55859375, "env_where_bbox50": 9.66796875, "env_where_iou": 21.109204924798952, "env_how_acc": 35.9375, "env_how_bbox50": 9.27734375, "env_how_iou": 20.803910767407036, "image_dual_sem": 12.351296164772728, "image_dual_evi": 5.4652931415929205 }, { "label": "Gemini 3 Flash", "group": "proprietary", "self_where_acc": 47.55859375, "self_where_bbox50": 33.59375, "self_where_iou": 33.84810160669598, "self_what_acc": 45.8984375, "self_what_bbox50": 37.5, "self_what_iou": 38.48590949512394, "env_where_acc": 56.15234375, "env_where_bbox50": 4.98046875, "env_where_iou": 13.524340531072504, "env_how_acc": 51.26953125, "env_how_bbox50": 5.078125, "env_how_iou": 12.243354844529359, "image_dual_sem": 24.935023238747554, "image_dual_evi": 1.991234756097561 }, { "label": "GPT-6 Astra", "group": "proprietary", "self_where_acc": 35.05859375, "self_where_bbox50": 27.83203125, "self_where_iou": 31.161509526825643, "self_what_acc": 42.96875, "self_what_bbox50": 27.83203125, "self_what_iou": 32.69433592503914, "env_where_acc": 57.2265625, "env_where_bbox50": 16.11328125, "env_where_iou": 24.330013508973828, "env_how_acc": 55.37109375, "env_how_bbox50": 14.94140625, "env_how_iou": 24.298371691166118, "image_dual_sem": 21.544736479028696, "image_dual_evi": 6.911586707746478 }, { "label": "GPT-5.6 Sol", "group": "proprietary", "self_where_acc": 34.08203125, "self_where_bbox50": 23.92578125, "self_where_iou": 28.822854840559124, "self_what_acc": 42.08984375, "self_what_bbox50": 24.609375, "self_what_iou": 30.078078595047756, "env_where_acc": 55.6640625, "env_where_bbox50": 12.890625, "env_where_iou": 23.016113855626067, "env_how_acc": 55.76171875, "env_how_bbox50": 12.5, "env_how_iou": 22.39197989372352, "image_dual_sem": 20.47610294117647, "image_dual_evi": 5.56640625 }, { "label": "GPT-5.6 Terra", "group": "proprietary", "self_where_acc": 33.69140625, "self_where_bbox50": 24.8046875, "self_where_iou": 28.863373364411103, "self_what_acc": 40.52734375, "self_what_bbox50": 27.05078125, "self_what_iou": 30.998061306103423, "env_where_acc": 58.88671875, "env_where_bbox50": 14.453125, "env_where_iou": 23.430746792899324, "env_how_acc": 60.15625, "env_how_bbox50": 12.890625, "env_how_iou": 22.50072861012638, "image_dual_sem": 22.333377944325484, "image_dual_evi": 6.31261927480916 }, { "label": "GPT-5.5", "group": "proprietary", "self_where_acc": 37.98828125, "self_where_bbox50": 19.43359375, "self_where_iou": 26.16517170369373, "self_what_acc": 53.41796875, "self_what_bbox50": 17.48046875, "self_what_iou": 26.325142160872122, "env_where_acc": 65.4296875, "env_where_bbox50": 17.578125, "env_where_iou": 25.06338518509504, "env_how_acc": 53.61328125, "env_how_bbox50": 17.87109375, "env_how_iou": 24.741223368305533, "image_dual_sem": 27.091733870967744, "image_dual_evi": 5.817407024793388 }, { "label": "GPT-5.4", "group": "proprietary", "self_where_acc": 37.890625, "self_where_bbox50": 12.20703125, "self_where_iou": 24.14637927961958, "self_what_acc": 37.59765625, "self_what_bbox50": 13.8671875, "self_what_iou": 25.858529254738098, "env_where_acc": 37.79296875, "env_where_bbox50": 12.890625, "env_where_iou": 24.446519067036483, "env_how_acc": 36.03515625, "env_how_bbox50": 12.01171875, "env_how_iou": 23.54725175589982, "image_dual_sem": 13.953917176573427, "image_dual_evi": 3.2169117647058822 }, { "label": "GPT-5.3", "group": "proprietary", "self_where_acc": 35.15625, "self_where_bbox50": 11.9140625, "self_where_iou": 23.477445399694453, "self_what_acc": 37.3046875, "self_what_bbox50": 13.8671875, "self_what_iou": 26.70147185505325, "env_where_acc": 56.54296875, "env_where_bbox50": 14.94140625, "env_where_iou": 22.51763096434379, "env_how_acc": 62.3046875, "env_how_bbox50": 15.4296875, "env_how_iou": 22.4503684562052, "image_dual_sem": 21.108019406392696, "image_dual_evi": 2.9296875 }, { "label": "MiMo-V2-Omni", "group": "proprietary", "self_where_acc": 28.7109375, "self_where_bbox50": 40.72265625, "self_where_iou": 36.5117634426247, "self_what_acc": 21.2890625, "self_what_bbox50": 36.9140625, "self_what_iou": 33.43712172583303, "env_where_acc": 36.5234375, "env_where_bbox50": 8.7890625, "env_where_iou": 17.60694353241879, "env_how_acc": 38.18359375, "env_how_bbox50": 9.1796875, "env_how_iou": 17.338113859194557, "image_dual_sem": 9.447487113402062, "image_dual_evi": 4.551809210526316 }, { "label": "Muse Spark 1.3 Contributor", "group": "proprietary", "self_where_acc": 38.671875, "self_where_bbox50": 20.5078125, "self_where_iou": 26.651530286110596, "self_what_acc": 48.6328125, "self_what_bbox50": 15.0390625, "self_what_iou": 21.238866550927174, "env_where_acc": 64.16015625, "env_where_bbox50": 14.84375, "env_where_iou": 25.531455026646206, "env_how_acc": 64.35546875, "env_how_bbox50": 14.94140625, "env_how_iou": 24.9048882729053, "image_dual_sem": 28.116349020442932, "image_dual_evi": 4.535381610576923 }, { "label": "Qwen3.7-Plus", "group": "proprietary", "self_where_acc": 33.30078125, "self_where_bbox50": 18.359375, "self_where_iou": 27.95283824369234, "self_what_acc": 34.5703125, "self_what_bbox50": 21.38671875, "self_what_iou": 30.27718135788073, "env_where_acc": 55.37109375, "env_where_bbox50": 18.359375, "env_where_iou": 26.687726251945904, "env_how_acc": 43.359375, "env_how_bbox50": 18.75, "env_how_iou": 26.96903476857638, "image_dual_sem": 15.74593653250774, "image_dual_evi": 6.4937734962406015 }, { "label": "Qwen3.6-Plus", "group": "proprietary", "self_where_acc": 32.8125, "self_where_bbox50": 16.6015625, "self_where_iou": 27.093338431821994, "self_what_acc": 33.49609375, "self_what_bbox50": 14.74609375, "self_what_iou": 26.080182812369408, "env_where_acc": 48.4375, "env_where_bbox50": 7.421875, "env_where_iou": 18.967861873916032, "env_how_acc": 42.48046875, "env_how_bbox50": 5.95703125, "env_how_iou": 19.863341153416172, "image_dual_sem": 13.716358985765126, "image_dual_evi": 1.556396484375 }, { "label": "Qwen3.6-Flash", "group": "proprietary", "self_where_acc": 25.09765625, "self_where_bbox50": 24.609375, "self_where_iou": 32.022019746820106, "self_what_acc": 28.7109375, "self_what_bbox50": 19.23828125, "self_what_iou": 29.827557950296907, "env_where_acc": 62.6953125, "env_where_bbox50": 19.43359375, "env_where_iou": 27.081448457206452, "env_how_acc": 56.73828125, "env_how_bbox50": 18.5546875, "env_how_iou": 25.805844228392242, "image_dual_sem": 15.966647553516818, "image_dual_evi": 6.0302734375 }, { "label": "Qwen3.5-Plus", "group": "proprietary", "self_where_acc": 28.61328125, "self_where_bbox50": 21.38671875, "self_where_iou": 27.079363493902314, "self_what_acc": 29.00390625, "self_what_bbox50": 12.3046875, "self_what_iou": 24.08682246874089, "env_where_acc": 47.55859375, "env_where_bbox50": 9.66796875, "env_where_iou": 19.316570037853676, "env_how_acc": 48.92578125, "env_how_bbox50": 8.30078125, "env_how_iou": 20.0086820612995, "image_dual_sem": 12.71373820754717, "image_dual_evi": 1.585751488095238 }, { "label": "Qwen3.5-Flash", "group": "proprietary", "self_where_acc": 27.83203125, "self_where_bbox50": 21.58203125, "self_where_iou": 29.821370906624463, "self_what_acc": 28.90625, "self_what_bbox50": 15.8203125, "self_what_iou": 23.134258690272056, "env_where_acc": 52.44140625, "env_where_bbox50": 8.7890625, "env_where_iou": 19.359071296425526, "env_how_acc": 54.4921875, "env_how_bbox50": 8.88671875, "env_how_iou": 20.057726159772965, "image_dual_sem": 15.04222289644013, "image_dual_evi": 2.30712890625 }, { "label": "GLM-5.3-Flash", "group": "open", "self_where_acc": 32.421875, "self_where_bbox50": 38.37890625, "self_where_iou": 38.10122360815056, "self_what_acc": 35.15625, "self_what_bbox50": 45.41015625, "self_what_iou": 43.82933162398782, "env_where_acc": 63.57421875, "env_where_bbox50": 32.71484375, "env_where_iou": 33.49064633863996, "env_how_acc": 57.421875, "env_how_bbox50": 33.0078125, "env_how_iou": 34.0962407819345, "image_dual_sem": 19.904641544117645, "image_dual_evi": 20.605005924170616 }, { "label": "GLM-4.6V", "group": "open", "self_where_acc": 30.76171875, "self_where_bbox50": 47.4609375, "self_where_iou": 42.98824729579403, "self_what_acc": 27.05078125, "self_what_bbox50": 44.921875, "self_what_iou": 42.30511684604162, "env_where_acc": 29.19921875, "env_where_bbox50": 9.47265625, "env_where_iou": 19.99178040075361, "env_how_acc": 44.23828125, "env_how_bbox50": 10.15625, "env_how_iou": 20.621228733186094, "image_dual_sem": 9.88188244047619, "image_dual_evi": 5.271629050925926 }, { "label": "GLM-4.5V", "group": "open", "self_where_acc": 31.93359375, "self_where_bbox50": 31.640625, "self_where_iou": 32.10519496276106, "self_what_acc": 29.00390625, "self_what_bbox50": 23.4375, "self_what_iou": 26.33234733328356, "env_where_acc": 19.921875, "env_where_bbox50": 15.91796875, "env_where_iou": 22.537174654624266, "env_how_acc": 39.6484375, "env_how_bbox50": 17.7734375, "env_how_iou": 24.16121257916204, "image_dual_sem": 8.75082671957672, "image_dual_evi": 7.706404320987654 }, { "label": "Intern-S1-Pro", "group": "open", "self_where_acc": 29.39453125, "self_where_bbox50": 17.3828125, "self_where_iou": 26.837094149538576, "self_what_acc": 26.171875, "self_what_bbox50": 10.546875, "self_what_iou": 22.649462885588903, "env_where_acc": 27.83203125, "env_where_bbox50": 2.734375, "env_where_iou": 13.674967030880609, "env_how_acc": 30.2734375, "env_how_bbox50": 3.22265625, "env_how_iou": 14.031416181858535, "image_dual_sem": 7.3125, "image_dual_evi": 0.4340277777777778 }, { "label": "InternVL 3.5-241B-A28B", "group": "open", "self_where_acc": 32.91015625, "self_where_bbox50": 31.34765625, "self_where_iou": 34.10822045493624, "self_what_acc": 26.07421875, "self_what_bbox50": 17.48046875, "self_what_iou": 24.760639388534056, "env_where_acc": 50.09765625, "env_where_bbox50": 5.37109375, "env_where_iou": 16.17070554211509, "env_how_acc": 41.796875, "env_how_bbox50": 5.17578125, "env_how_iou": 15.260990930804494, "image_dual_sem": 12.968322308394162, "image_dual_evi": 1.7045454545454544 }, { "label": "InternVL 3.5-30B-A3B", "group": "open", "self_where_acc": 27.34375, "self_where_bbox50": 4.8828125, "self_where_iou": 20.003980894926464, "self_what_acc": 24.0234375, "self_what_bbox50": 7.03125, "self_what_iou": 15.286177543143193, "env_where_acc": 35.3515625, "env_where_bbox50": 0.5859375, "env_where_iou": 7.556639455561663, "env_how_acc": 41.30859375, "env_how_bbox50": 1.26953125, "env_how_iou": 7.2955108308066565, "image_dual_sem": 9.077830981182796, "image_dual_evi": 0 }, { "label": "InternVL 3.5-14B", "group": "open", "self_where_acc": 22.75390625, "self_where_bbox50": 7.6171875, "self_where_iou": 22.21861384746123, "self_what_acc": 31.93359375, "self_what_bbox50": 7.51953125, "self_what_iou": 22.462431927691366, "env_where_acc": 28.515625, "env_where_bbox50": 4.6875, "env_where_iou": 12.923612717831134, "env_how_acc": 41.30859375, "env_how_bbox50": 4.98046875, "env_how_iou": 11.947063995394986, "image_dual_sem": 8.720128676470589, "image_dual_evi": 0.5696614583333333 }, { "label": "InternVL 3.5-8B", "group": "open", "self_where_acc": 28.515625, "self_where_bbox50": 19.7265625, "self_where_iou": 34.241167452149526, "self_what_acc": 24.51171875, "self_what_bbox50": 9.47265625, "self_what_iou": 29.0950867528341, "env_where_acc": 24.70703125, "env_where_bbox50": 4.19921875, "env_where_iou": 12.266134380259789, "env_how_acc": 30.76171875, "env_how_bbox50": 2.5390625, "env_how_iou": 11.427632990133533, "image_dual_sem": 7.179054054054054, "image_dual_evi": 0.5974264705882353 }, { "label": "InternVL 3.5-4B", "group": "open", "self_where_acc": 25.5859375, "self_where_bbox50": 3.125, "self_where_iou": 19.784410102267646, "self_what_acc": 26.3671875, "self_what_bbox50": 12.01171875, "self_what_iou": 23.731435943322467, "env_where_acc": 22.36328125, "env_where_bbox50": 0.9765625, "env_where_iou": 8.05130476364124, "env_how_acc": 36.71875, "env_how_bbox50": 0.9765625, "env_how_iou": 7.490303106084714, "image_dual_sem": 7.0609177215189876, "image_dual_evi": 0 }, { "label": "Kimi K2.5", "group": "open", "self_where_acc": 34.27734375, "self_where_bbox50": 27.05078125, "self_where_iou": 30.402903866024094, "self_what_acc": 32.71484375, "self_what_bbox50": 18.45703125, "self_what_iou": 23.896418203275395, "env_where_acc": 39.35546875, "env_where_bbox50": 4.98046875, "env_where_iou": 15.554994000998812, "env_how_acc": 30.078125, "env_how_bbox50": 4.6875, "env_how_iou": 14.356529746285373, "image_dual_sem": 10.674137443438914, "image_dual_evi": 1.125 }, { "label": "Kimi K2.6", "group": "open", "self_where_acc": 36.1328125, "self_where_bbox50": 22.0703125, "self_where_iou": 28.492953004734396, "self_what_acc": 32.32421875, "self_what_bbox50": 12.20703125, "self_what_iou": 20.830172706846916, "env_where_acc": 42.7734375, "env_where_bbox50": 12.3046875, "env_where_iou": 21.949971634669975, "env_how_acc": 28.02734375, "env_how_bbox50": 10.83984375, "env_how_iou": 20.42914757373632, "image_dual_sem": 11.286501024590164, "image_dual_evi": 3.6850527108433737 }, { "label": "MiMo-V2.5", "group": "open", "self_where_acc": 33.10546875, "self_where_bbox50": 43.26171875, "self_where_iou": 38.26521551094516, "self_what_acc": 27.34375, "self_what_bbox50": 43.45703125, "self_what_iou": 40.14641277866936, "env_where_acc": 51.171875, "env_where_bbox50": 26.5625, "env_where_iou": 30.74854920494686, "env_how_acc": 49.70703125, "env_how_bbox50": 27.83203125, "env_how_iou": 31.487149645288444, "image_dual_sem": 15.336061507936508, "image_dual_evi": 19.04246794871795 }, { "label": "Qwen3.8-27B", "group": "open", "self_where_acc": 26.171875, "self_where_bbox50": 34.66796875, "self_where_iou": 35.18871903727147, "self_what_acc": 28.80859375, "self_what_bbox50": 16.9921875, "self_what_iou": 26.080440988531745, "env_where_acc": 61.9140625, "env_where_bbox50": 22.75390625, "env_where_iou": 27.62862757181531, "env_how_acc": 49.4140625, "env_how_bbox50": 21.875, "env_how_iou": 28.07647404128823, "image_dual_sem": 15.264327076677317, "image_dual_evi": 8.45959595959596 }, { "label": "Qwen3.6-27B", "group": "open", "self_where_acc": 30.76171875, "self_where_bbox50": 36.03515625, "self_where_iou": 35.230658795946, "self_what_acc": 36.42578125, "self_what_bbox50": 13.18359375, "self_what_iou": 22.813335557438485, "env_where_acc": 60.3515625, "env_where_bbox50": 21.6796875, "env_where_iou": 27.8472752337803, "env_how_acc": 53.41796875, "env_how_bbox50": 19.53125, "env_how_iou": 27.27273872846565, "image_dual_sem": 18.36144728116711, "image_dual_evi": 6.234375 }, { "label": "Qwen3.5-397B-A17B", "group": "open", "self_where_acc": 27.44140625, "self_where_bbox50": 3.3203125, "self_where_iou": 12.57857271713905, "self_what_acc": 35.83984375, "self_what_bbox50": 13.4765625, "self_what_iou": 23.53911893189798, "env_where_acc": 47.94921875, "env_where_bbox50": 2.83203125, "env_where_iou": 13.011113502795574, "env_how_acc": 46.19140625, "env_how_bbox50": 4.39453125, "env_how_iou": 13.858524486546525, "image_dual_sem": 14.074337121212121, "image_dual_evi": 0.18136160714285715 }, { "label": "Qwen3.5-122B-A10B", "group": "open", "self_where_acc": 32.6171875, "self_where_bbox50": 29.1015625, "self_where_iou": 31.582646397765934, "self_what_acc": 37.79296875, "self_what_bbox50": 25.9765625, "self_what_iou": 31.62226498858958, "env_where_acc": 49.70703125, "env_where_bbox50": 6.0546875, "env_where_iou": 19.388978361518873, "env_how_acc": 49.0234375, "env_how_bbox50": 6.8359375, "env_how_iou": 18.778407539101806, "image_dual_sem": 15.401785714285715, "image_dual_evi": 2.1440972222222223 }, { "label": "Qwen3.5-35B-A3B", "group": "open", "self_where_acc": 29.4921875, "self_where_bbox50": 27.63671875, "self_where_iou": 30.47749474855459, "self_what_acc": 27.44140625, "self_what_bbox50": 0.5859375, "self_what_iou": 0.8414639464736662, "env_where_acc": 53.22265625, "env_where_bbox50": 6.0546875, "env_where_iou": 14.510394570379622, "env_how_acc": 57.51953125, "env_how_bbox50": 7.2265625, "env_how_iou": 18.533249166098923, "image_dual_sem": 15.52488698899371, "image_dual_evi": 0 }, { "label": "Qwen3.5-27B", "group": "open", "self_where_acc": 31.640625, "self_where_bbox50": 42.7734375, "self_where_iou": 39.8853082751578, "self_what_acc": 37.109375, "self_what_bbox50": 22.75390625, "self_what_iou": 28.502998005119668, "env_where_acc": 57.8125, "env_where_bbox50": 7.32421875, "env_where_iou": 20.380142122282187, "env_how_acc": 50.5859375, "env_how_bbox50": 7.51953125, "env_how_iou": 20.959987270273203, "image_dual_sem": 17.764852335164836, "image_dual_evi": 2.9017857142857144 }, { "label": "Qwen3.5-9B", "group": "open", "self_where_acc": 29.00390625, "self_where_bbox50": 15.91796875, "self_where_iou": 25.812597432235023, "self_what_acc": 29.00390625, "self_what_bbox50": 22.94921875, "self_what_iou": 32.485194228746245, "env_where_acc": 53.22265625, "env_where_bbox50": 10.25390625, "env_where_iou": 20.895423746461457, "env_how_acc": 52.24609375, "env_how_bbox50": 11.5234375, "env_how_iou": 22.14576053314587, "image_dual_sem": 15.052336165048544, "image_dual_evi": 2.778151939655172 }, { "label": "Qwen3.5-4B", "group": "open", "self_where_acc": 30.859375, "self_where_bbox50": 12.890625, "self_where_iou": 23.21018338976616, "self_what_acc": 30.17578125, "self_what_bbox50": 12.40234375, "self_what_iou": 23.09610589162234, "env_where_acc": 47.4609375, "env_where_bbox50": 6.8359375, "env_where_iou": 17.77007527580784, "env_how_acc": 47.4609375, "env_how_bbox50": 6.34765625, "env_how_iou": 17.9607170200453, "image_dual_sem": 15.4296875, "image_dual_evi": 1.1637369791666665 }, { "label": "SpaceOm", "group": "specialized", "self_where_acc": 24.70703125, "self_where_bbox50": 2.83203125, "self_where_iou": 6.67593108146661, "self_what_acc": 24.51171875, "self_what_bbox50": 4.19921875, "self_what_iou": 11.394461367796884, "env_where_acc": 35.15625, "env_where_bbox50": 2.44140625, "env_where_iou": 8.590030727970321, "env_how_acc": 32.8125, "env_how_bbox50": 1.7578125, "env_how_iou": 6.47737847647762, "image_dual_sem": 7.98875762195122, "image_dual_evi": 0.13020833333333331 }, { "label": "SpaceR", "group": "specialized", "self_where_acc": 20.60546875, "self_where_bbox50": 2.5390625, "self_where_iou": 6.253679675097253, "self_what_acc": 24.0234375, "self_what_bbox50": 1.07421875, "self_what_iou": 1.827479935108782, "env_where_acc": 42.3828125, "env_where_bbox50": 2.1484375, "env_where_iou": 6.499989676954455, "env_how_acc": 48.828125, "env_how_bbox50": 2.34375, "env_how_iou": 6.931860054981212, "image_dual_sem": 9.415443497474747, "image_dual_evi": 0 }, { "label": "SpaceThinker", "group": "specialized", "self_where_acc": 22.55859375, "self_where_bbox50": 1.171875, "self_where_iou": 3.0263144756086833, "self_what_acc": 25.390625, "self_what_bbox50": 1.7578125, "self_what_iou": 5.918726980712663, "env_where_acc": 32.8125, "env_where_bbox50": 0.5859375, "env_where_iou": 5.0929581258976935, "env_how_acc": 34.27734375, "env_how_bbox50": 0.68359375, "env_how_iou": 4.660499710124178, "image_dual_sem": 7.89086612654321, "image_dual_evi": 0 }, { "label": "ViLaSR", "group": "specialized", "self_where_acc": 18.84765625, "self_where_bbox50": 4.296875, "self_where_iou": 7.633668705445462, "self_what_acc": 22.0703125, "self_what_bbox50": 1.953125, "self_what_iou": 3.545554354079953, "env_where_acc": 43.06640625, "env_where_bbox50": 1.85546875, "env_where_iou": 3.501944867868133, "env_how_acc": 49.70703125, "env_how_bbox50": 1.46484375, "env_how_iou": 3.1684692897542313, "image_dual_sem": 9.666982323232324, "image_dual_evi": 0.27901785714285715 } ], "video": [ { "label": "Gemini 3.8 Flash", "group": "proprietary", "composite_acc": 56.423611111111114, "composite_tiou50": 41.40461215932913, "composite_mtiou": 43.01590302189875, "atomic_acc": 38.76951661561152, "atomic_f150": 17.15629304407713, "atomic_mtiou": 14.562189655549423, "visibility_acc": 45.99609375, "visibility_f150": 25.273097914088293, "visibility_mtiou": 29.025372362743312, "video_dual_sem": 6.93359375, "video_dual_evi": 8.203125 }, { "label": "Gemini 3.1 Pro Preview", "group": "proprietary", "composite_acc": 54.844606946983546, "composite_tiou50": 40.1736225933991, "composite_mtiou": 37.92894809144247, "atomic_acc": 32.929086173587436, "atomic_f150": 8.976476292268748, "atomic_mtiou": 8.633910963624288, "visibility_acc": 33.49609375, "visibility_f150": 20.394452518429755, "visibility_mtiou": 30.293871063458678, "video_dual_sem": 1.171875, "video_dual_evi": 2.05078125 }, { "label": "Gemini 3.1 Flash Lite", "group": "proprietary", "composite_acc": 23.688663282571913, "composite_tiou50": 23.011844331641285, "composite_mtiou": 25.99017273363958, "atomic_acc": 19.658398446997452, "atomic_f150": 11.569297053819506, "atomic_mtiou": 10.30939389860425, "visibility_acc": 52.83203125, "visibility_f150": 44.09715082339188, "visibility_mtiou": 42.19576068547335, "video_dual_sem": 7.32421875, "video_dual_evi": 5.46875 }, { "label": "Gemini 3 Flash", "group": "proprietary", "composite_acc": 48.29351535836178, "composite_tiou50": 47.69487199838815, "composite_mtiou": 52.44081373565918, "atomic_acc": 34.99391304881126, "atomic_f150": 27.547249081283663, "atomic_mtiou": 22.007774820701194, "visibility_acc": 55.17578125, "visibility_f150": 45.0104785588578, "visibility_mtiou": 44.316189752911804, "video_dual_sem": 11.42578125, "video_dual_evi": 12.59765625 }, { "label": "MiMo-V2-Omni", "group": "proprietary", "composite_acc": 26.923076923076923, "composite_tiou50": 24.998777446329896, "composite_mtiou": 26.937585529092985, "atomic_acc": 30.109631065231362, "atomic_f150": 21.297215898801653, "atomic_mtiou": 17.384666328588597, "visibility_acc": 59.375, "visibility_f150": 52.67197792309612, "visibility_mtiou": 53.71213679175349, "video_dual_sem": 10.64453125, "video_dual_evi": 11.5234375 }, { "label": "Muse Spark 1.3 Contributor", "group": "proprietary", "composite_acc": 49.18032786885246, "composite_tiou50": 49.97992707389823, "composite_mtiou": 53.07844868124456, "atomic_acc": 39.16603112369986, "atomic_f150": 27.166918075474268, "atomic_mtiou": 22.3132317087884, "visibility_acc": 47.8515625, "visibility_f150": 47.9809777617956, "visibility_mtiou": 44.16078094977718, "video_dual_sem": 12.59765625, "video_dual_evi": 16.2109375 }, { "label": "Qwen3.7-Plus", "group": "proprietary", "composite_acc": 6.545454545454546, "composite_tiou50": 6.181818181818182, "composite_mtiou": 6.392504689886591, "atomic_acc": 33.78092083146571, "atomic_f150": 24.20363576256625, "atomic_mtiou": 18.302956545721948, "visibility_acc": 53.61328125, "visibility_f150": 56.7990894670728, "visibility_mtiou": 49.24068901552238, "video_dual_sem": 13.96484375, "video_dual_evi": 11.5234375 }, { "label": "Qwen3.6-Plus", "group": "proprietary", "composite_acc": 9.818181818181818, "composite_tiou50": 9.272727272727273, "composite_mtiou": 9.554141085339156, "atomic_acc": 30.091530717685377, "atomic_f150": 15.558275365940158, "atomic_mtiou": 15.265476181613295, "visibility_acc": 50.78125, "visibility_f150": 52.15818667655229, "visibility_mtiou": 46.10515820304889, "video_dual_sem": 14.84375, "video_dual_evi": 8.49609375 }, { "label": "Qwen3.6-Flash", "group": "proprietary", "composite_acc": 32.323232323232325, "composite_tiou50": 28.07232747262732, "composite_mtiou": 32.04490201701736, "atomic_acc": 24.858389521835054, "atomic_f150": 16.888450766509433, "atomic_mtiou": 12.922640646181252, "visibility_acc": 52.24609375, "visibility_f150": 52.69170011880643, "visibility_mtiou": 46.683495854922555, "video_dual_sem": 11.5234375, "video_dual_evi": 7.32421875 }, { "label": "Qwen3.5-Plus", "group": "proprietary", "composite_acc": 2.4344569288389515, "composite_tiou50": 2.434456928838951, "composite_mtiou": 2.4677093867413484, "atomic_acc": 32.07344358694369, "atomic_f150": 17.4504154935647, "atomic_mtiou": 17.00067463856963, "visibility_acc": 53.22265625, "visibility_f150": 54.218971296940666, "visibility_mtiou": 46.78082261784201, "video_dual_sem": 14.35546875, "video_dual_evi": 9.08203125 }, { "label": "Qwen3.5-Flash", "group": "proprietary", "composite_acc": 32.593856655290104, "composite_tiou50": 29.82075807955783, "composite_mtiou": 33.09766894398415, "atomic_acc": 26.913222446236563, "atomic_f150": 17.761643478321755, "atomic_mtiou": 13.910831939479031, "visibility_acc": 52.34375, "visibility_f150": 58.27779580246657, "visibility_mtiou": 51.301233698926275, "video_dual_sem": 9.27734375, "video_dual_evi": 9.47265625 }, { "label": "GLM-5.3-Flash", "group": "open", "composite_acc": 26.022304832713754, "composite_tiou50": 24.502418001776487, "composite_mtiou": 25.840913915393042, "atomic_acc": 30.33459185001953, "atomic_f150": 21.195474708165982, "atomic_mtiou": 17.98882679289778, "visibility_acc": 49.12109375, "visibility_f150": 43.94609576303189, "visibility_mtiou": 41.40330935892236, "video_dual_sem": 11.81640625, "video_dual_evi": 9.375 }, { "label": "GLM-4.6V", "group": "open", "composite_acc": 31.161971830985912, "composite_tiou50": 1.232394366197183, "composite_mtiou": 6.011941749270345, "atomic_acc": 32.17686656270297, "atomic_f150": 7.450047203668805, "atomic_mtiou": 6.233073094402071, "visibility_acc": 31.25, "visibility_f150": 17.358742493102117, "visibility_mtiou": 33.808814308339514, "video_dual_sem": 0.09765625, "video_dual_evi": 0.48828125 }, { "label": "InternVL 3.5-30B-A3B", "group": "open", "composite_acc": 13.333333333333334, "composite_tiou50": 1.9298245614035088, "composite_mtiou": 4.324977908024443, "atomic_acc": 24.4691012198465, "atomic_f150": 5.771545271754535, "atomic_mtiou": 5.370018652699706, "visibility_acc": 43.9453125, "visibility_f150": 8.152396504676437, "visibility_mtiou": 12.586025935849193, "video_dual_sem": 7.2265625, "video_dual_evi": 0.29296875 }, { "label": "InternVL 3.5-14B", "group": "open", "composite_acc": 23.39791356184799, "composite_tiou50": 2.2534842206973353, "composite_mtiou": 7.326322757227012, "atomic_acc": 21.776605620495697, "atomic_f150": 3.92479904646619, "atomic_mtiou": 3.8050211885356915, "visibility_acc": 54.4921875, "visibility_f150": 14.360825779867547, "visibility_mtiou": 22.66236961133018, "video_dual_sem": 3.02734375, "video_dual_evi": 0.87890625 }, { "label": "InternVL 3.5-8B", "group": "open", "composite_acc": 22.425249169435215, "composite_tiou50": 6.2281284606866, "composite_mtiou": 10.585174542639662, "atomic_acc": 22.947114477611848, "atomic_f150": 4.229693661498476, "atomic_mtiou": 4.6121508253577845, "visibility_acc": 51.85546875, "visibility_f150": 16.685833421770894, "visibility_mtiou": 21.31504053892709, "video_dual_sem": 6.4453125, "video_dual_evi": 0.29296875 }, { "label": "InternVL 3.5-4B", "group": "open", "composite_acc": 25.833333333333336, "composite_tiou50": 2.3333333333333335, "composite_mtiou": 5.790689994485705, "atomic_acc": 20.686579320650527, "atomic_f150": 4.334954246723264, "atomic_mtiou": 3.4137053594037896, "visibility_acc": 34.5703125, "visibility_f150": 17.106127192663706, "visibility_mtiou": 32.3062786974221, "video_dual_sem": 0.390625, "video_dual_evi": 0.48828125 }, { "label": "Kimi K2.5", "group": "open", "composite_acc": 13.263525305410123, "composite_tiou50": 12.390924956369982, "composite_mtiou": 13.244650727300286, "atomic_acc": 30.00092508048999, "atomic_f150": 21.17947400503148, "atomic_mtiou": 17.64136173355417, "visibility_acc": 50.48828125, "visibility_f150": 50.26418870549122, "visibility_mtiou": 45.8170863445863, "video_dual_sem": 11.5234375, "video_dual_evi": 10.15625 }, { "label": "Kimi K2.6", "group": "open", "composite_acc": 11.937716262975778, "composite_tiou50": 10.68321589173893, "composite_mtiou": 11.137142583557239, "atomic_acc": 31.415506321669262, "atomic_f150": 19.964166734173116, "atomic_mtiou": 16.72009268683071, "visibility_acc": 39.94140625, "visibility_f150": 48.30834035565635, "visibility_mtiou": 43.29570308101801, "video_dual_sem": 8.49609375, "video_dual_evi": 7.8125 }, { "label": "MiMo-V2.5", "group": "open", "composite_acc": 35.59602649006622, "composite_tiou50": 33.36072173927333, "composite_mtiou": 36.92664150078057, "atomic_acc": 29.46469142432254, "atomic_f150": 21.414169067497653, "atomic_mtiou": 17.951709733027123, "visibility_acc": 58.49609375, "visibility_f150": 54.35634653705363, "visibility_mtiou": 50.4367377300544, "video_dual_sem": 11.9140625, "video_dual_evi": 9.9609375 }, { "label": "Qwen3.8-27B", "group": "open", "composite_acc": 15.257352941176471, "composite_tiou50": 6.8014705882352935, "composite_mtiou": 7.481583296895794, "atomic_acc": 27.773976579087062, "atomic_f150": 12.351450040393653, "atomic_mtiou": 8.64166413367578, "visibility_acc": 43.1640625, "visibility_f150": 16.308021744784003, "visibility_mtiou": 23.645939768689285, "video_dual_sem": 8.88671875, "video_dual_evi": 0.48828125 }, { "label": "Qwen3.6-27B", "group": "open", "composite_acc": 19.926873857404022, "composite_tiou50": 12.79707495429616, "composite_mtiou": 14.08318806243853, "atomic_acc": 29.103445608742085, "atomic_f150": 18.882934067755222, "atomic_mtiou": 15.8374796200289, "visibility_acc": 52.734375, "visibility_f150": 43.323069038034134, "visibility_mtiou": 42.331847230566616, "video_dual_sem": 13.37890625, "video_dual_evi": 7.71484375 }, { "label": "Qwen3.5-397B-A17B", "group": "open", "composite_acc": 5.1923076923076925, "composite_tiou50": 0.9615384615384616, "composite_mtiou": 1.503478123483182, "atomic_acc": 26.625008334444612, "atomic_f150": 10.26606482316853, "atomic_mtiou": 8.449795930182646, "visibility_acc": 40.4296875, "visibility_f150": 21.221252698802033, "visibility_mtiou": 31.7740811117785, "video_dual_sem": 5.6640625, "video_dual_evi": 1.85546875 }, { "label": "Qwen3.5-122B-A10B", "group": "open", "composite_acc": 20.97053726169844, "composite_tiou50": 17.80752023006827, "composite_mtiou": 19.936756523285514, "atomic_acc": 23.44445879318281, "atomic_f150": 13.311628562117727, "atomic_mtiou": 11.86148477800694, "visibility_acc": 48.4375, "visibility_f150": 46.66273945909445, "visibility_mtiou": 49.74858600323111, "video_dual_sem": 5.37109375, "video_dual_evi": 6.54296875 }, { "label": "Qwen3.5-35B-A3B", "group": "open", "composite_acc": 20.973782771535582, "composite_tiou50": 15.68338084856616, "composite_mtiou": 16.672496183639907, "atomic_acc": 27.69642232723426, "atomic_f150": 17.75665104758943, "atomic_mtiou": 16.01121924891034, "visibility_acc": 54.1015625, "visibility_f150": 50.009721000279804, "visibility_mtiou": 48.60428072954879, "video_dual_sem": 8.88671875, "video_dual_evi": 8.984375 }, { "label": "Qwen3.5-27B", "group": "open", "composite_acc": 14.616755793226382, "composite_tiou50": 13.368983957219251, "composite_mtiou": 14.260117445488715, "atomic_acc": 29.706853905435317, "atomic_f150": 20.098459171073642, "atomic_mtiou": 17.665513606157496, "visibility_acc": 51.3671875, "visibility_f150": 52.170709097672365, "visibility_mtiou": 48.66111115835457, "video_dual_sem": 11.23046875, "video_dual_evi": 9.66796875 }, { "label": "Qwen3.5-9B", "group": "open", "composite_acc": 9.506398537477148, "composite_tiou50": 7.266622974946248, "composite_mtiou": 8.283776327920886, "atomic_acc": 28.22211859641467, "atomic_f150": 17.83275708116131, "atomic_mtiou": 15.982537984746076, "visibility_acc": 50.68359375, "visibility_f150": 33.84843000532734, "visibility_mtiou": 36.78899875360025, "video_dual_sem": 8.0078125, "video_dual_evi": 5.95703125 }, { "label": "Qwen3.5-4B", "group": "open", "composite_acc": 6.367041198501873, "composite_tiou50": 1.1235955056179776, "composite_mtiou": 1.1262452402737906, "atomic_acc": 9.99630905511811, "atomic_f150": 0.8973817567567568, "atomic_mtiou": 0.7889970850440372, "visibility_acc": 33.88671875, "visibility_f150": 45.17947134008842, "visibility_mtiou": 51.98611456676373, "video_dual_sem": 0.5859375, "video_dual_evi": 0.390625 }, { "label": "SpaceOm", "group": "specialized", "composite_acc": 26.54424040066778, "composite_tiou50": 0, "composite_mtiou": 2.4884093173689177, "atomic_acc": 25.86365782558669, "atomic_f150": 3.9863238406265813, "atomic_mtiou": 3.0717565023767373, "visibility_acc": 32.32421875, "visibility_f150": 17.648061754797144, "visibility_mtiou": 34.22804090417127, "video_dual_sem": 0.29296875, "video_dual_evi": 0 }, { "label": "SpaceR", "group": "specialized", "composite_acc": 21.428571428571427, "composite_tiou50": 0, "composite_mtiou": 1.882552734087687, "atomic_acc": 26.17176276756214, "atomic_f150": 3.959800286640079, "atomic_mtiou": 3.504858859487095, "visibility_acc": 33.69140625, "visibility_f150": 16.469940156672788, "visibility_mtiou": 30.754046799947716, "video_dual_sem": 0.390625, "video_dual_evi": 0 }, { "label": "SpaceThinker", "group": "specialized", "composite_acc": 17.173524150268335, "composite_tiou50": 0, "composite_mtiou": 1.2575868298918116, "atomic_acc": 23.06532557354926, "atomic_f150": 3.711253055909864, "atomic_mtiou": 2.637264173189676, "visibility_acc": 33.69140625, "visibility_f150": 14.331195661511103, "visibility_mtiou": 27.08581055255871, "video_dual_sem": 0.87890625, "video_dual_evi": 0 }, { "label": "ViLaSR", "group": "specialized", "composite_acc": 5.192878338278932, "composite_tiou50": 0, "composite_mtiou": 0.4096667370935645, "atomic_acc": 9.862261136500603, "atomic_f150": 0.4268973214285714, "atomic_mtiou": 1.0782481631876215, "visibility_acc": 35.9375, "visibility_f150": 10.440443373581418, "visibility_mtiou": 20.6015781503597, "video_dual_sem": 1.5625, "video_dual_evi": 0 } ], "overall": [ { "label": "Gemini 3.8 Flash", "group": "proprietary", "position_dual_sem": 38.28125, "position_dual_evi": 32.51953125, "action_observation_dual_sem": 52.83203125, "action_observation_dual_evi": 36.23046875, "behavior_visibility_dual_sem": 6.93359375, "behavior_visibility_dual_evi": 8.203125, "dual_sem": 11.99396471562256, "dual_evi": 13.237960327801398 }, { "label": "Gemini 3.1 Pro Preview", "group": "proprietary", "position_dual_sem": 26.953125, "position_dual_evi": 29.4921875, "action_observation_dual_sem": 27.1484375, "action_observation_dual_evi": 30.76171875, "behavior_visibility_dual_sem": 1.171875, "behavior_visibility_dual_evi": 2.05078125, "dual_sem": 2.246430445210613, "dual_evi": 3.840049214632634 }, { "label": "Gemini 3.1 Flash Lite", "group": "proprietary", "position_dual_sem": 15.52734375, "position_dual_evi": 6.0546875, "action_observation_dual_sem": 10.25390625, "action_observation_dual_evi": 4.98046875, "behavior_visibility_dual_sem": 7.32421875, "behavior_visibility_dual_evi": 5.46875, "dual_sem": 9.195550444162437, "dual_evi": 5.467021024343978 }, { "label": "Gemini 3 Flash", "group": "proprietary", "position_dual_sem": 25.5859375, "position_dual_evi": 1.85546875, "action_observation_dual_sem": 24.31640625, "action_observation_dual_evi": 2.1484375, "behavior_visibility_dual_sem": 11.42578125, "behavior_visibility_dual_evi": 12.59765625, "dual_sem": 15.67083704530045, "dual_evi": 3.43890306122449 }, { "label": "MiMo-V2-Omni", "group": "proprietary", "position_dual_sem": 9.9609375, "position_dual_evi": 5.2734375, "action_observation_dual_sem": 8.984375, "action_observation_dual_evi": 4.00390625, "behavior_visibility_dual_sem": 10.64453125, "behavior_visibility_dual_evi": 11.5234375, "dual_sem": 10.010350378313374, "dual_evi": 6.525870475764164 }, { "label": "Muse Spark 1.3 Contributor", "group": "proprietary", "position_dual_sem": 24.70703125, "position_dual_evi": 6.73828125, "action_observation_dual_sem": 32.6171875, "action_observation_dual_evi": 3.41796875, "behavior_visibility_dual_sem": 12.59765625, "behavior_visibility_dual_evi": 16.2109375, "dual_sem": 17.399423005021923, "dual_evi": 7.087791085815153 }, { "label": "Qwen3.7-Plus", "group": "proprietary", "position_dual_sem": 16.40625, "position_dual_evi": 6.54296875, "action_observation_dual_sem": 15.13671875, "action_observation_dual_evi": 6.4453125, "behavior_visibility_dual_sem": 13.96484375, "behavior_visibility_dual_evi": 11.5234375, "dual_sem": 14.802003938169717, "dual_evi": 8.306567874317386 }, { "label": "Qwen3.6-Plus", "group": "proprietary", "position_dual_sem": 13.4765625, "position_dual_evi": 1.66015625, "action_observation_dual_sem": 13.96484375, "action_observation_dual_evi": 1.46484375, "behavior_visibility_dual_sem": 14.84375, "behavior_visibility_dual_evi": 8.49609375, "dual_sem": 14.257802993429058, "dual_evi": 2.6308487021857925 }, { "label": "Qwen3.6-Flash", "group": "proprietary", "position_dual_sem": 15.91796875, "position_dual_evi": 7.421875, "action_observation_dual_sem": 16.015625, "action_observation_dual_evi": 5.078125, "behavior_visibility_dual_sem": 11.5234375, "behavior_visibility_dual_evi": 7.32421875, "dual_sem": 13.385965507876152, "dual_evi": 6.614559529250457 }, { "label": "Qwen3.5-Plus", "group": "proprietary", "position_dual_sem": 11.23046875, "position_dual_evi": 3.02734375, "action_observation_dual_sem": 14.6484375, "action_observation_dual_evi": 1.07421875, "behavior_visibility_dual_sem": 14.35546875, "behavior_visibility_dual_evi": 9.08203125, "dual_sem": 13.484818511333469, "dual_evi": 2.7000633445945947 }, { "label": "Qwen3.5-Flash", "group": "proprietary", "position_dual_sem": 14.2578125, "position_dual_evi": 2.63671875, "action_observation_dual_sem": 15.91796875, "action_observation_dual_evi": 2.05078125, "behavior_visibility_dual_sem": 9.27734375, "behavior_visibility_dual_evi": 9.47265625, "dual_sem": 11.476509808189627, "dual_evi": 3.710532707253886 }, { "label": "GLM-5.3-Flash", "group": "open", "position_dual_sem": 19.3359375, "position_dual_evi": 20.703125, "action_observation_dual_sem": 20.5078125, "action_observation_dual_evi": 20.5078125, "behavior_visibility_dual_sem": 11.81640625, "behavior_visibility_dual_evi": 9.375, "dual_sem": 14.829354457171315, "dual_evi": 12.886717302704707 }, { "label": "GLM-4.6V", "group": "open", "position_dual_sem": 8.30078125, "position_dual_evi": 5.17578125, "action_observation_dual_sem": 12.20703125, "action_observation_dual_evi": 5.37109375, "behavior_visibility_dual_sem": 0.09765625, "behavior_visibility_dual_evi": 0.48828125, "dual_sem": 0.1934012406803355, "dual_evi": 0.8937769819466248 }, { "label": "InternVL 3.5-30B-A3B", "group": "open", "position_dual_sem": 9.27734375, "position_dual_evi": 0, "action_observation_dual_sem": 8.88671875, "action_observation_dual_evi": 0.09765625, "behavior_visibility_dual_sem": 7.2265625, "behavior_visibility_dual_evi": 0.29296875, "dual_sem": 8.04709638854898, "dual_evi": 0 }, { "label": "InternVL 3.5-14B", "group": "open", "position_dual_sem": 6.4453125, "position_dual_evi": 0.68359375, "action_observation_dual_sem": 13.4765625, "action_observation_dual_evi": 0.48828125, "behavior_visibility_dual_sem": 3.02734375, "behavior_visibility_dual_evi": 0.87890625, "dual_sem": 4.494384168704156, "dual_evi": 0.6912745786516855 }, { "label": "InternVL 3.5-8B", "group": "open", "position_dual_sem": 6.640625, "position_dual_evi": 1.26953125, "action_observation_dual_sem": 7.8125, "action_observation_dual_evi": 0.390625, "behavior_visibility_dual_sem": 6.4453125, "behavior_visibility_dual_evi": 0.29296875, "dual_sem": 6.792425416505229, "dual_evi": 0.39314516129032256 }, { "label": "InternVL 3.5-4B", "group": "open", "position_dual_sem": 5.46875, "position_dual_evi": 0.09765625, "action_observation_dual_sem": 9.9609375, "action_observation_dual_evi": 0, "behavior_visibility_dual_sem": 0.390625, "behavior_visibility_dual_evi": 0.48828125, "dual_sem": 0.7402952886529529, "dual_evi": 0 }, { "label": "Kimi K2.5", "group": "open", "position_dual_sem": 11.9140625, "position_dual_evi": 1.5625, "action_observation_dual_sem": 9.66796875, "action_observation_dual_evi": 0.87890625, "behavior_visibility_dual_sem": 11.5234375, "behavior_visibility_dual_evi": 10.15625, "dual_sem": 11.082539962973284, "dual_evi": 2.025623268698061 }, { "label": "Kimi K2.6", "group": "open", "position_dual_sem": 14.6484375, "position_dual_evi": 5.2734375, "action_observation_dual_sem": 9.1796875, "action_observation_dual_evi": 2.83203125, "behavior_visibility_dual_sem": 8.49609375, "behavior_visibility_dual_evi": 7.8125, "dual_sem": 9.694498816460307, "dual_evi": 5.007930822758904 }, { "label": "MiMo-V2.5", "group": "open", "position_dual_sem": 16.2109375, "position_dual_evi": 18.9453125, "action_observation_dual_sem": 14.55078125, "action_observation_dual_evi": 19.140625, "behavior_visibility_dual_sem": 11.9140625, "behavior_visibility_dual_evi": 9.9609375, "dual_sem": 13.410199179731052, "dual_evi": 13.079900801187971 }, { "label": "Qwen3.8-27B", "group": "open", "position_dual_sem": 15.8203125, "position_dual_evi": 13.0859375, "action_observation_dual_sem": 14.74609375, "action_observation_dual_evi": 6.25, "behavior_visibility_dual_sem": 8.88671875, "behavior_visibility_dual_evi": 0.48828125, "dual_sem": 11.233449897942046, "dual_evi": 0.9232719656046743 }, { "label": "Qwen3.6-27B", "group": "open", "position_dual_sem": 17.48046875, "position_dual_evi": 12.98828125, "action_observation_dual_sem": 19.3359375, "action_observation_dual_evi": 4.1015625, "behavior_visibility_dual_sem": 13.37890625, "behavior_visibility_dual_evi": 7.71484375, "dual_sem": 15.479101803187712, "dual_evi": 6.896046275553067 }, { "label": "Qwen3.5-397B-A17B", "group": "open", "position_dual_sem": 12.01171875, "position_dual_evi": 0.09765625, "action_observation_dual_sem": 16.9921875, "action_observation_dual_evi": 1.26953125, "behavior_visibility_dual_sem": 5.6640625, "behavior_visibility_dual_evi": 1.85546875, "dual_sem": 8.077445652173914, "dual_evi": 0.3304259417808219 }, { "label": "Qwen3.5-122B-A10B", "group": "open", "position_dual_sem": 13.4765625, "position_dual_evi": 2.5390625, "action_observation_dual_sem": 17.96875, "action_observation_dual_evi": 1.85546875, "behavior_visibility_dual_sem": 5.37109375, "behavior_visibility_dual_evi": 6.54296875, "dual_sem": 7.964657488247147, "dual_evi": 3.229804209342993 }, { "label": "Qwen3.5-35B-A3B", "group": "open", "position_dual_sem": 15.33203125, "position_dual_evi": 2.44140625, "action_observation_dual_sem": 15.72265625, "action_observation_dual_evi": 0, "behavior_visibility_dual_sem": 8.88671875, "behavior_visibility_dual_evi": 8.984375, "dual_sem": 11.30325516246918, "dual_evi": 0 }, { "label": "Qwen3.5-27B", "group": "open", "position_dual_sem": 17.3828125, "position_dual_evi": 3.80859375, "action_observation_dual_sem": 18.1640625, "action_observation_dual_evi": 2.34375, "behavior_visibility_dual_sem": 11.23046875, "behavior_visibility_dual_evi": 9.66796875, "dual_sem": 13.761366422702542, "dual_evi": 4.463790233074361 }, { "label": "Qwen3.5-9B", "group": "open", "position_dual_sem": 14.35546875, "position_dual_evi": 2.44140625, "action_observation_dual_sem": 15.8203125, "action_observation_dual_evi": 3.22265625, "behavior_visibility_dual_sem": 8.0078125, "behavior_visibility_dual_evi": 5.95703125, "dual_sem": 10.454077070142258, "dual_evi": 3.7891679115265995 }, { "label": "Qwen3.5-4B", "group": "open", "position_dual_sem": 15.4296875, "position_dual_evi": 1.07421875, "action_observation_dual_sem": 15.4296875, "action_observation_dual_evi": 1.26953125, "behavior_visibility_dual_sem": 0.5859375, "behavior_visibility_dual_evi": 0.390625, "dual_sem": 1.1290015243902438, "dual_evi": 0.5849149214659686 }, { "label": "SpaceOm", "group": "specialized", "position_dual_sem": 8.3984375, "position_dual_evi": 0.1953125, "action_observation_dual_sem": 7.6171875, "action_observation_dual_evi": 0.09765625, "behavior_visibility_dual_sem": 0.29296875, "behavior_visibility_dual_evi": 0, "dual_sem": 0.565209771354616, "dual_evi": 0 }, { "label": "SpaceR", "group": "specialized", "position_dual_sem": 8.10546875, "position_dual_evi": 0.1953125, "action_observation_dual_sem": 11.23046875, "action_observation_dual_evi": 0, "behavior_visibility_dual_sem": 0.390625, "behavior_visibility_dual_evi": 0, "dual_sem": 0.7501288854240017, "dual_evi": 0 }, { "label": "SpaceThinker", "group": "specialized", "position_dual_sem": 7.51953125, "position_dual_evi": 0, "action_observation_dual_sem": 8.30078125, "action_observation_dual_evi": 0, "behavior_visibility_dual_sem": 0.87890625, "behavior_visibility_dual_evi": 0, "dual_sem": 1.58164459891394, "dual_evi": 0 }, { "label": "ViLaSR", "group": "specialized", "position_dual_sem": 9.5703125, "position_dual_evi": 0.48828125, "action_observation_dual_sem": 9.765625, "action_observation_dual_evi": 0.1953125, "behavior_visibility_dual_sem": 1.5625, "behavior_visibility_dual_evi": 0, "dual_sem": 2.6901791988756147, "dual_evi": 0 } ], "mediaCorrelations": [ { "label": "Image: Dual Semantic vs Dual Evidence", "n": 45, "pearson": 0.6499071324155364, "spearman": 0.5204949880589153 }, { "label": "Video: Dual Semantic vs Dual Evidence", "n": 32, "pearson": 0.8300286502120859, "spearman": 0.8048293622771658 }, { "label": "Cross-media: Image vs Video Dual Semantic", "n": 32, "pearson": 0.2735582997182115, "spearman": 0.49317079507146866 } ], "taskCorrelations": [ { "label": "Landmark-relative Position", "n": 45, "pearson": 0.4822390080183948, "spearman": 0.30668379632543685 }, { "label": "Future Observation", "n": 45, "pearson": 0.5859624837242299, "spearman": 0.4783697430373178 }, { "label": "Self-relative Position", "n": 45, "pearson": 0.5805297721763, "spearman": 0.6753871513840713 }, { "label": "Action Decision", "n": 45, "pearson": 0.4857736262482636, "spearman": 0.5090921069969693 }, { "label": "Composite Behavior", "n": 32, "pearson": 0.8206718322857796, "spearman": 0.6303433214963571 }, { "label": "Atomic Behavior", "n": 32, "pearson": 0.7385748723227312, "spearman": 0.7327712609970675 }, { "label": "Landmark Visibility", "n": 32, "pearson": 0.6588498514102328, "spearman": 0.5882137317344954 } ], "pairedCoverage": [ { "id": "position", "title": "Position", "agent": "Landmark-relative Position", "world": "Self-relative Position", "medium": "image", "models": 45, "min": 1024, "max": 1024 }, { "id": "action_observation", "title": "Action-Observation", "agent": "Future Observation", "world": "Action Decision", "medium": "image", "models": 45, "min": 1024, "max": 1024 }, { "id": "behavior_visibility", "title": "Behavior-Visibility", "agent": "Flight Behavior", "world": "Landmark Visibility", "medium": "video", "models": 32, "min": 1024, "max": 1024 } ], "matchedPairRows": [ { "label": "Claude Opus 4.8", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 39.35546875, "worldSem": 54.1015625, "dualSem": 19.3359375, "agentEvi": 11.42578125, "worldEvi": 10.44921875, "dualEvi": 2.44140625, "independentSem": 21.29192352294922, "independentEvi": 1.1939048767089844, "semanticPhi": -0.08034586410620916, "evidencePhi": 0.128194034142615, "agentGivenWorld": 35.74007220216607, "worldGivenAgent": 49.13151364764268 }, { "label": "Claude Opus 4.7", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 39.2578125, "worldSem": 49.70703125, "dualSem": 19.23828125, "agentEvi": 8.203125, "worldEvi": 7.12890625, "dualEvi": 1.171875, "independentSem": 19.513893127441406, "independentEvi": 0.5847930908203125, "semanticPhi": -0.011288262971154244, "evidencePhi": 0.08314638134096991, "agentGivenWorld": 38.70333988212181, "worldGivenAgent": 49.004975124378106 }, { "label": "Claude Opus 4.6", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 38.0859375, "worldSem": 62.01171875, "dualSem": 22.55859375, "agentEvi": 2.1484375, "worldEvi": 8.59375, "dualEvi": 0, "independentSem": 23.61774444580078, "independentEvi": 0.18463134765625, "semanticPhi": -0.0449385518763444, "evidencePhi": -0.04543399138563119, "agentGivenWorld": 36.37795275590551, "worldGivenAgent": 59.23076923076923 }, { "label": "Claude Sonnet 4.6", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 37.6953125, "worldSem": 48.53515625, "dualSem": 16.11328125, "agentEvi": 4.8828125, "worldEvi": 9.5703125, "dualEvi": 0.29296875, "independentSem": 18.29547882080078, "independentEvi": 0.4673004150390625, "semanticPhi": -0.09009620280695112, "evidencePhi": -0.027497498029897177, "agentGivenWorld": 33.199195171026155, "worldGivenAgent": 42.74611398963731 }, { "label": "Gemini 3.8 Flash", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 60.05859375, "worldSem": 61.9140625, "dualSem": 38.28125, "agentEvi": 66.69921875, "worldEvi": 40.8203125, "dualEvi": 32.51953125, "independentSem": 37.184715270996094, "independentEvi": 27.226829528808594, "semanticPhi": 0.04610480186276591, "evidencePhi": 0.22848902174653252, "agentGivenWorld": 61.82965299684543, "worldGivenAgent": 63.739837398373986 }, { "label": "Gemini 3.1 Pro Preview", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 40.91796875, "worldSem": 63.671875, "dualSem": 26.953125, "agentEvi": 58.7890625, "worldEvi": 37.5, "dualEvi": 29.4921875, "independentSem": 26.053237915039062, "independentEvi": 22.0458984375, "semanticPhi": 0.03805467047229643, "evidencePhi": 0.31248540245017603, "agentGivenWorld": 42.331288343558285, "worldGivenAgent": 65.8711217183771 }, { "label": "Gemini 3.1 Flash Lite", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 33.69140625, "worldSem": 47.55859375, "dualSem": 15.52734375, "agentEvi": 48.14453125, "worldEvi": 9.66796875, "dualEvi": 6.0546875, "independentSem": 16.02315902709961, "independentEvi": 4.654598236083984, "semanticPhi": -0.021005051917151227, "evidencePhi": 0.094819236681383, "agentGivenWorld": 32.648870636550306, "worldGivenAgent": 46.08695652173913 }, { "label": "Gemini 3 Flash", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 47.55859375, "worldSem": 56.15234375, "dualSem": 25.5859375, "agentEvi": 33.59375, "worldEvi": 4.98046875, "dualEvi": 1.85546875, "independentSem": 26.705265045166016, "independentEvi": 1.673126220703125, "semanticPhi": -0.04516982294976636, "evidencePhi": 0.017746499538357687, "agentGivenWorld": 45.565217391304344, "worldGivenAgent": 53.798767967145785 }, { "label": "GPT-6 Astra", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 35.05859375, "worldSem": 57.2265625, "dualSem": 18.5546875, "agentEvi": 27.83203125, "worldEvi": 16.11328125, "dualEvi": 7.32421875, "independentSem": 20.062828063964844, "independentEvi": 4.484653472900391, "semanticPhi": -0.06388484188615759, "evidencePhi": 0.17233304705593216, "agentGivenWorld": 32.42320819112628, "worldGivenAgent": 52.92479108635098 }, { "label": "GPT-5.6 Sol", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 34.08203125, "worldSem": 55.6640625, "dualSem": 18.359375, "agentEvi": 23.92578125, "worldEvi": 12.890625, "dualEvi": 5.56640625, "independentSem": 18.97144317626953, "independentEvi": 3.0841827392578125, "semanticPhi": -0.025993799132663375, "evidencePhi": 0.17362794865180792, "agentGivenWorld": 32.98245614035088, "worldGivenAgent": 53.86819484240688 }, { "label": "GPT-5.6 Terra", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 33.69140625, "worldSem": 58.88671875, "dualSem": 19.53125, "agentEvi": 24.8046875, "worldEvi": 14.453125, "dualEvi": 7.12890625, "independentSem": 19.839763641357422, "independentEvi": 3.585052490234375, "semanticPhi": -0.013265699227556698, "evidencePhi": 0.23336223398162206, "agentGivenWorld": 33.16749585406302, "worldGivenAgent": 57.971014492753625 }, { "label": "GPT-5.5", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 37.98828125, "worldSem": 65.4296875, "dualSem": 25.1953125, "agentEvi": 19.43359375, "worldEvi": 17.578125, "dualEvi": 6.640625, "independentSem": 24.855613708496094, "independentEvi": 3.4160614013671875, "semanticPhi": 0.014716116574348447, "evidencePhi": 0.21409665003833112, "agentGivenWorld": 38.50746268656716, "worldGivenAgent": 66.32390745501286 }, { "label": "GPT-5.4", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 37.890625, "worldSem": 37.79296875, "dualSem": 14.35546875, "agentEvi": 12.20703125, "worldEvi": 12.890625, "dualEvi": 3.90625, "independentSem": 14.319992065429688, "independentEvi": 1.5735626220703125, "semanticPhi": 0.0015082499534461741, "evidencePhi": 0.21264354681974593, "agentGivenWorld": 37.98449612403101, "worldGivenAgent": 37.88659793814433 }, { "label": "GPT-5.3", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 35.15625, "worldSem": 56.54296875, "dualSem": 18.9453125, "agentEvi": 11.9140625, "worldEvi": 14.94140625, "dualEvi": 2.9296875, "independentSem": 19.878387451171875, "independentEvi": 1.7801284790039062, "semanticPhi": -0.03942410715872418, "evidencePhi": 0.09953898550088658, "agentGivenWorld": 33.506044905008636, "worldGivenAgent": 53.888888888888886 }, { "label": "MiMo-V2-Omni", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 28.7109375, "worldSem": 36.5234375, "dualSem": 9.9609375, "agentEvi": 40.72265625, "worldEvi": 8.7890625, "dualEvi": 5.2734375, "independentSem": 10.486221313476562, "independentEvi": 3.5791397094726562, "semanticPhi": -0.024113838997216704, "evidencePhi": 0.12179587839760028, "agentGivenWorld": 27.27272727272727, "worldGivenAgent": 34.69387755102041 }, { "label": "Muse Spark 1.3 Contributor", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 38.671875, "worldSem": 64.16015625, "dualSem": 24.70703125, "agentEvi": 20.5078125, "worldEvi": 14.84375, "dualEvi": 6.73828125, "independentSem": 24.811935424804688, "independentEvi": 3.04412841796875, "semanticPhi": -0.004492101424941554, "evidencePhi": 0.2573433119010313, "agentGivenWorld": 38.50837138508371, "worldGivenAgent": 63.888888888888886 }, { "label": "Qwen3.7-Plus", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 33.30078125, "worldSem": 55.37109375, "dualSem": 16.40625, "agentEvi": 18.359375, "worldEvi": 18.359375, "dualEvi": 6.54296875, "independentSem": 18.439006805419922, "independentEvi": 3.37066650390625, "semanticPhi": -0.08676571823503988, "evidencePhi": 0.2116461366181411, "agentGivenWorld": 29.629629629629626, "worldGivenAgent": 49.266862170087975 }, { "label": "Qwen3.6-Plus", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 32.8125, "worldSem": 48.4375, "dualSem": 13.4765625, "agentEvi": 16.6015625, "worldEvi": 7.421875, "dualEvi": 1.66015625, "independentSem": 15.8935546875, "independentEvi": 1.232147216796875, "semanticPhi": -0.10300386063623707, "evidencePhi": 0.04388220959299214, "agentGivenWorld": 27.82258064516129, "worldGivenAgent": 41.07142857142857 }, { "label": "Qwen3.6-Flash", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 25.09765625, "worldSem": 62.6953125, "dualSem": 15.91796875, "agentEvi": 24.609375, "worldEvi": 19.43359375, "dualEvi": 7.421875, "independentSem": 15.735054016113281, "independentEvi": 4.7824859619140625, "semanticPhi": 0.008723387481604743, "evidencePhi": 0.1548605826377769, "agentGivenWorld": 25.38940809968847, "worldGivenAgent": 63.42412451361867 }, { "label": "Qwen3.5-Plus", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 28.61328125, "worldSem": 47.55859375, "dualSem": 11.23046875, "agentEvi": 21.38671875, "worldEvi": 9.66796875, "dualEvi": 3.02734375, "independentSem": 13.608074188232422, "independentEvi": 2.0676612854003906, "semanticPhi": -0.10534054879916496, "evidencePhi": 0.07919887478619396, "agentGivenWorld": 23.613963039014372, "worldGivenAgent": 39.249146757679185 }, { "label": "Qwen3.5-Flash", "groupId": "proprietary", "pair": "position", "n": 1024, "agentSem": 27.83203125, "worldSem": 52.44140625, "dualSem": 14.2578125, "agentEvi": 21.58203125, "worldEvi": 8.7890625, "dualEvi": 2.63671875, "independentSem": 14.595508575439453, "independentEvi": 1.8968582153320312, "semanticPhi": -0.015087929777575494, "evidencePhi": 0.0635186373855673, "agentGivenWorld": 27.188081936685286, "worldGivenAgent": 51.2280701754386 }, { "label": "GLM-5.3-Flash", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 32.421875, "worldSem": 63.57421875, "dualSem": 19.3359375, "agentEvi": 38.37890625, "worldEvi": 32.71484375, "dualEvi": 20.703125, "independentSem": 20.611953735351562, "independentEvi": 12.555599212646484, "semanticPhi": -0.05664859124515053, "evidencePhi": 0.3570941106681799, "agentGivenWorld": 30.414746543778804, "worldGivenAgent": 59.63855421686747 }, { "label": "GLM-4.6V", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 30.76171875, "worldSem": 29.19921875, "dualSem": 8.30078125, "agentEvi": 47.4609375, "worldEvi": 9.47265625, "dualEvi": 5.17578125, "independentSem": 8.982181549072266, "independentEvi": 4.495811462402344, "semanticPhi": -0.03247276287391513, "evidencePhi": 0.04650016813181452, "agentGivenWorld": 28.428093645484946, "worldGivenAgent": 26.984126984126984 }, { "label": "GLM-4.5V", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 31.93359375, "worldSem": 19.921875, "dualSem": 7.12890625, "agentEvi": 31.640625, "worldEvi": 15.91796875, "dualEvi": 9.1796875, "independentSem": 6.3617706298828125, "independentEvi": 5.0365447998046875, "semanticPhi": 0.04119644935733611, "evidencePhi": 0.24350781399759264, "agentGivenWorld": 35.78431372549019, "worldGivenAgent": 22.32415902140673 }, { "label": "Intern-S1-Pro", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 29.39453125, "worldSem": 27.83203125, "dualSem": 7.6171875, "agentEvi": 17.3828125, "worldEvi": 2.734375, "dualEvi": 0.48828125, "independentSem": 8.181095123291016, "independentEvi": 0.475311279296875, "semanticPhi": -0.02761918336489233, "evidencePhi": 0.002098625960152025, "agentGivenWorld": 27.368421052631582, "worldGivenAgent": 25.91362126245847 }, { "label": "InternVL 3.5-241B-A28B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 32.91015625, "worldSem": 50.09765625, "dualSem": 15.72265625, "agentEvi": 31.34765625, "worldEvi": 5.37109375, "dualEvi": 3.125, "independentSem": 16.48721694946289, "independentEvi": 1.6837120056152344, "semanticPhi": -0.03254238898769934, "evidencePhi": 0.13780890133251703, "agentGivenWorld": 31.384015594541907, "worldGivenAgent": 47.774480712166174 }, { "label": "InternVL 3.5-30B-A3B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 27.34375, "worldSem": 35.3515625, "dualSem": 9.27734375, "agentEvi": 4.8828125, "worldEvi": 0.5859375, "dualEvi": 0, "independentSem": 9.66644287109375, "independentEvi": 0.0286102294921875, "semanticPhi": -0.01826044679718953, "evidencePhi": -0.017394312168851834, "agentGivenWorld": 26.243093922651934, "worldGivenAgent": 33.92857142857143 }, { "label": "InternVL 3.5-14B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 22.75390625, "worldSem": 28.515625, "dualSem": 6.4453125, "agentEvi": 7.6171875, "worldEvi": 4.6875, "dualEvi": 0.68359375, "independentSem": 6.4884185791015625, "independentEvi": 0.3570556640625, "semanticPhi": -0.0022773263242011435, "evidencePhi": 0.058236512450021885, "agentGivenWorld": 22.602739726027394, "worldGivenAgent": 28.32618025751073 }, { "label": "InternVL 3.5-8B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 28.515625, "worldSem": 24.70703125, "dualSem": 6.640625, "agentEvi": 19.7265625, "worldEvi": 4.19921875, "dualEvi": 1.26953125, "independentSem": 7.0453643798828125, "independentEvi": 0.8283615112304688, "semanticPhi": -0.0207845659462057, "evidencePhi": 0.05527456118301621, "agentGivenWorld": 26.877470355731226, "worldGivenAgent": 23.28767123287671 }, { "label": "InternVL 3.5-4B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 25.5859375, "worldSem": 22.36328125, "dualSem": 5.46875, "agentEvi": 3.125, "worldEvi": 0.9765625, "dualEvi": 0.09765625, "independentSem": 5.721855163574219, "independentEvi": 0.030517578125, "semanticPhi": -0.013921033600318846, "evidencePhi": 0.039239445025860395, "agentGivenWorld": 24.45414847161572, "worldGivenAgent": 21.374045801526716 }, { "label": "Kimi K2.5", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 34.27734375, "worldSem": 39.35546875, "dualSem": 11.9140625, "agentEvi": 27.05078125, "worldEvi": 4.98046875, "dualEvi": 1.5625, "independentSem": 13.490009307861328, "independentEvi": 1.3472557067871094, "semanticPhi": -0.06796448879769944, "evidencePhi": 0.022273571757811732, "agentGivenWorld": 30.272952853598017, "worldGivenAgent": 34.75783475783476 }, { "label": "Kimi K2.6", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 36.1328125, "worldSem": 42.7734375, "dualSem": 14.6484375, "agentEvi": 22.0703125, "worldEvi": 12.3046875, "dualEvi": 5.2734375, "independentSem": 15.455245971679688, "independentEvi": 2.7156829833984375, "semanticPhi": -0.03394648123272233, "evidencePhi": 0.18774987968714926, "agentGivenWorld": 34.24657534246575, "worldGivenAgent": 40.54054054054054 }, { "label": "MiMo-V2.5", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 33.10546875, "worldSem": 51.171875, "dualSem": 16.2109375, "agentEvi": 43.26171875, "worldEvi": 26.5625, "dualEvi": 18.9453125, "independentSem": 16.940689086914062, "independentEvi": 11.49139404296875, "semanticPhi": -0.031022670552330017, "evidencePhi": 0.3406443963221426, "agentGivenWorld": 31.679389312977097, "worldGivenAgent": 48.96755162241888 }, { "label": "Qwen3.8-27B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 26.171875, "worldSem": 61.9140625, "dualSem": 15.8203125, "agentEvi": 34.66796875, "worldEvi": 22.75390625, "dualEvi": 13.0859375, "independentSem": 16.204071044921875, "independentEvi": 7.888317108154297, "semanticPhi": -0.01797847062498251, "evidencePhi": 0.2605019827842978, "agentGivenWorld": 25.55205047318612, "worldGivenAgent": 60.447761194029844 }, { "label": "Qwen3.6-27B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 30.76171875, "worldSem": 60.3515625, "dualSem": 17.48046875, "agentEvi": 36.03515625, "worldEvi": 21.6796875, "dualEvi": 12.98828125, "independentSem": 18.56517791748047, "independentEvi": 7.812309265136719, "semanticPhi": -0.04804825006162903, "evidencePhi": 0.26163408728263765, "agentGivenWorld": 28.964401294498384, "worldGivenAgent": 56.82539682539682 }, { "label": "Qwen3.5-397B-A17B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 27.44140625, "worldSem": 47.94921875, "dualSem": 12.01171875, "agentEvi": 3.3203125, "worldEvi": 2.83203125, "dualEvi": 0.09765625, "independentSem": 13.157939910888672, "independentEvi": 0.09403228759765625, "semanticPhi": -0.05141814655277674, "evidencePhi": 0.001219315238515848, "agentGivenWorld": 25.050916496945007, "worldGivenAgent": 43.77224199288256 }, { "label": "Qwen3.5-122B-A10B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 32.6171875, "worldSem": 49.70703125, "dualSem": 13.4765625, "agentEvi": 29.1015625, "worldEvi": 6.0546875, "dualEvi": 2.5390625, "independentSem": 16.213035583496094, "independentEvi": 1.7620086669921875, "semanticPhi": -0.11674298927964072, "evidencePhi": 0.07172840887911591, "agentGivenWorld": 27.111984282907663, "worldGivenAgent": 41.31736526946108 }, { "label": "Qwen3.5-35B-A3B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 29.4921875, "worldSem": 53.22265625, "dualSem": 15.33203125, "agentEvi": 27.63671875, "worldEvi": 6.0546875, "dualEvi": 2.44140625, "independentSem": 15.696525573730469, "independentEvi": 1.6733169555664062, "semanticPhi": -0.01601963455546714, "evidencePhi": 0.07201549045388361, "agentGivenWorld": 28.807339449541285, "worldGivenAgent": 51.98675496688742 }, { "label": "Qwen3.5-27B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 31.640625, "worldSem": 57.8125, "dualSem": 17.3828125, "agentEvi": 42.7734375, "worldEvi": 7.32421875, "dualEvi": 3.80859375, "independentSem": 18.292236328125, "independentEvi": 3.1328201293945312, "semanticPhi": -0.03959514981362671, "evidencePhi": 0.0524265822926706, "agentGivenWorld": 30.067567567567565, "worldGivenAgent": 54.93827160493827 }, { "label": "Qwen3.5-9B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 29.00390625, "worldSem": 53.22265625, "dualSem": 14.35546875, "agentEvi": 15.91796875, "worldEvi": 10.25390625, "dualEvi": 2.44140625, "independentSem": 15.436649322509766, "independentEvi": 1.6322135925292969, "semanticPhi": -0.047751465941189786, "evidencePhi": 0.07291284820882848, "agentGivenWorld": 26.972477064220186, "worldGivenAgent": 49.494949494949495 }, { "label": "Qwen3.5-4B", "groupId": "open", "pair": "position", "n": 1024, "agentSem": 30.859375, "worldSem": 47.4609375, "dualSem": 15.4296875, "agentEvi": 12.890625, "worldEvi": 6.8359375, "dualEvi": 1.07421875, "independentSem": 14.646148681640625, "independentEvi": 0.881195068359375, "semanticPhi": 0.033969643410173056, "evidencePhi": 0.022825374300576417, "agentGivenWorld": 32.510288065843625, "worldGivenAgent": 50 }, { "label": "SpaceOm", "groupId": "specialized", "pair": "position", "n": 1024, "agentSem": 24.70703125, "worldSem": 35.15625, "dualSem": 8.3984375, "agentEvi": 2.83203125, "worldEvi": 2.44140625, "dualEvi": 0.1953125, "independentSem": 8.686065673828125, "independentEvi": 0.06914138793945312, "semanticPhi": -0.013967175736380526, "evidencePhi": 0.04928293414664297, "agentGivenWorld": 23.88888888888889, "worldGivenAgent": 33.99209486166008 }, { "label": "SpaceR", "groupId": "specialized", "pair": "position", "n": 1024, "agentSem": 20.60546875, "worldSem": 42.3828125, "dualSem": 8.10546875, "agentEvi": 2.5390625, "worldEvi": 2.1484375, "dualEvi": 0.1953125, "independentSem": 8.733177185058594, "independentEvi": 0.0545501708984375, "semanticPhi": -0.031405123596726564, "evidencePhi": 0.06171478376821427, "agentGivenWorld": 19.12442396313364, "worldGivenAgent": 39.33649289099526 }, { "label": "SpaceThinker", "groupId": "specialized", "pair": "position", "n": 1024, "agentSem": 22.55859375, "worldSem": 32.8125, "dualSem": 7.51953125, "agentEvi": 1.171875, "worldEvi": 0.5859375, "dualEvi": 0, "independentSem": 7.40203857421875, "independentEvi": 0.006866455078125, "semanticPhi": 0.005986931186450848, "evidencePhi": -0.00835991964335238, "agentGivenWorld": 22.916666666666664, "worldGivenAgent": 33.33333333333333 }, { "label": "ViLaSR", "groupId": "specialized", "pair": "position", "n": 1024, "agentSem": 18.84765625, "worldSem": 43.06640625, "dualSem": 9.5703125, "agentEvi": 4.296875, "worldEvi": 1.85546875, "dualEvi": 0.48828125, "independentSem": 8.117008209228516, "independentEvi": 0.0797271728515625, "semanticPhi": 0.07504534017111707, "evidencePhi": 0.14929671594125846, "agentGivenWorld": 22.22222222222222, "worldGivenAgent": 50.77720207253886 }, { "label": "Claude Opus 4.8", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 35.9375, "worldSem": 51.85546875, "dualSem": 19.7265625, "agentEvi": 14.2578125, "worldEvi": 8.0078125, "dualEvi": 2.5390625, "independentSem": 18.63555908203125, "independentEvi": 1.1417388916015625, "semanticPhi": 0.04550713299164667, "evidencePhi": 0.14724509838781813, "agentGivenWorld": 38.04143126177024, "worldGivenAgent": 54.891304347826086 }, { "label": "Claude Opus 4.7", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 37.20703125, "worldSem": 39.0625, "dualSem": 14.74609375, "agentEvi": 7.03125, "worldEvi": 7.91015625, "dualEvi": 0.9765625, "independentSem": 14.53399658203125, "independentEvi": 0.556182861328125, "semanticPhi": 0.008993826764485952, "evidencePhi": 0.060919805435919544, "agentGivenWorld": 37.75, "worldGivenAgent": 39.63254593175853 }, { "label": "Claude Opus 4.6", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 32.421875, "worldSem": 58.88671875, "dualSem": 18.84765625, "agentEvi": 2.83203125, "worldEvi": 9.1796875, "dualEvi": 0.29296875, "independentSem": 19.092178344726562, "independentEvi": 0.25997161865234375, "semanticPhi": -0.010616863354986806, "evidencePhi": 0.00688906303221079, "agentGivenWorld": 32.00663349917081, "worldGivenAgent": 58.13253012048193 }, { "label": "Claude Sonnet 4.6", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 23.6328125, "worldSem": 61.03515625, "dualSem": 15.72265625, "agentEvi": 3.61328125, "worldEvi": 8.59375, "dualEvi": 0.09765625, "independentSem": 14.424324035644531, "independentEvi": 0.310516357421875, "semanticPhi": 0.06266834566477318, "evidencePhi": -0.040696352976094155, "agentGivenWorld": 25.759999999999998, "worldGivenAgent": 66.52892561983471 }, { "label": "Gemini 3.8 Flash", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 74.90234375, "worldSem": 69.53125, "dualSem": 52.83203125, "agentEvi": 73.828125, "worldEvi": 42.28515625, "dualEvi": 36.23046875, "independentSem": 52.080535888671875, "independentEvi": 31.218338012695312, "semanticPhi": 0.0376569099679806, "evidencePhi": 0.2308109032634775, "agentGivenWorld": 75.98314606741573, "worldGivenAgent": 70.53455019556715 }, { "label": "Gemini 3.1 Pro Preview", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 58.7890625, "worldSem": 47.16796875, "dualSem": 27.1484375, "agentEvi": 59.86328125, "worldEvi": 37.109375, "dualEvi": 30.76171875, "independentSem": 27.72960662841797, "independentEvi": 22.214889526367188, "semanticPhi": -0.023652430816760675, "evidencePhi": 0.36092674044871065, "agentGivenWorld": 57.55693581780539, "worldGivenAgent": 46.179401993355484 }, { "label": "Gemini 3.1 Flash Lite", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 30.078125, "worldSem": 35.9375, "dualSem": 10.25390625, "agentEvi": 47.94921875, "worldEvi": 9.27734375, "dualEvi": 4.98046875, "independentSem": 10.809326171875, "independentEvi": 4.448413848876953, "semanticPhi": -0.025241413294356238, "evidencePhi": 0.036709828129011544, "agentGivenWorld": 28.532608695652172, "worldGivenAgent": 34.090909090909086 }, { "label": "Gemini 3 Flash", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 45.8984375, "worldSem": 51.26953125, "dualSem": 24.31640625, "agentEvi": 37.5, "worldEvi": 5.078125, "dualEvi": 2.1484375, "independentSem": 23.53191375732422, "independentEvi": 1.904296875, "semanticPhi": 0.03149596863736353, "evidencePhi": 0.022969395294297864, "agentGivenWorld": 47.42857142857143, "worldGivenAgent": 52.97872340425533 }, { "label": "GPT-6 Astra", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 42.96875, "worldSem": 55.37109375, "dualSem": 25.68359375, "agentEvi": 27.83203125, "worldEvi": 14.94140625, "dualEvi": 6.54296875, "independentSem": 23.792266845703125, "independentEvi": 4.158496856689453, "semanticPhi": 0.0768571228289001, "evidencePhi": 0.1492425561373325, "agentGivenWorld": 46.38447971781305, "worldGivenAgent": 59.77272727272728 }, { "label": "GPT-5.6 Sol", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 42.08984375, "worldSem": 55.76171875, "dualSem": 23.14453125, "agentEvi": 24.609375, "worldEvi": 12.5, "dualEvi": 5.56640625, "independentSem": 23.470020294189453, "independentEvi": 3.076171875, "semanticPhi": -0.013274040897852371, "evidencePhi": 0.17481239661039724, "agentGivenWorld": 41.5061295971979, "worldGivenAgent": 54.988399071925755 }, { "label": "GPT-5.6 Terra", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 40.52734375, "worldSem": 60.15625, "dualSem": 26.07421875, "agentEvi": 27.05078125, "worldEvi": 12.890625, "dualEvi": 5.6640625, "independentSem": 24.379730224609375, "independentEvi": 3.4870147705078125, "semanticPhi": 0.07049939876439598, "evidencePhi": 0.1462508118774656, "agentGivenWorld": 43.34415584415584, "worldGivenAgent": 64.33734939759036 }, { "label": "GPT-5.5", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 53.41796875, "worldSem": 53.61328125, "dualSem": 29.296875, "agentEvi": 17.48046875, "worldEvi": 17.87109375, "dualEvi": 5.17578125, "independentSem": 28.63912582397461, "independentEvi": 3.123950958251953, "semanticPhi": 0.02644078813533758, "evidencePhi": 0.14101422915066922, "agentGivenWorld": 54.644808743169406, "worldGivenAgent": 54.844606946983546 }, { "label": "GPT-5.4", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 37.59765625, "worldSem": 36.03515625, "dualSem": 13.57421875, "agentEvi": 13.8671875, "worldEvi": 12.01171875, "dualEvi": 2.734375, "independentSem": 13.54837417602539, "independentEvi": 1.6656875610351562, "semanticPhi": 0.001111359750074854, "evidencePhi": 0.09511679369490342, "agentGivenWorld": 37.669376693766935, "worldGivenAgent": 36.103896103896105 }, { "label": "GPT-5.3", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 37.3046875, "worldSem": 62.3046875, "dualSem": 23.828125, "agentEvi": 13.8671875, "worldEvi": 15.4296875, "dualEvi": 2.9296875, "independentSem": 23.242568969726562, "independentEvi": 2.1396636962890625, "semanticPhi": 0.024984184822058917, "evidencePhi": 0.06328111692966783, "agentGivenWorld": 38.24451410658307, "worldGivenAgent": 63.87434554973822 }, { "label": "MiMo-V2-Omni", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 21.2890625, "worldSem": 38.18359375, "dualSem": 8.984375, "agentEvi": 36.9140625, "worldEvi": 9.1796875, "dualEvi": 4.00390625, "independentSem": 8.128929138183594, "independentEvi": 3.3885955810546875, "semanticPhi": 0.043013664329669916, "evidencePhi": 0.04415976958911745, "agentGivenWorld": 23.52941176470588, "worldGivenAgent": 42.201834862385326 }, { "label": "Muse Spark 1.3 Contributor", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 48.6328125, "worldSem": 64.35546875, "dualSem": 32.6171875, "agentEvi": 15.0390625, "worldEvi": 14.94140625, "dualEvi": 3.41796875, "independentSem": 31.297874450683594, "independentEvi": 2.2470474243164062, "semanticPhi": 0.05511262392252067, "evidencePhi": 0.09188674120679623, "agentGivenWorld": 50.682852807283766, "worldGivenAgent": 67.06827309236948 }, { "label": "Qwen3.7-Plus", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 34.5703125, "worldSem": 43.359375, "dualSem": 15.13671875, "agentEvi": 21.38671875, "worldEvi": 18.75, "dualEvi": 6.4453125, "independentSem": 14.989471435546875, "independentEvi": 4.010009765625, "semanticPhi": 0.006247449895839119, "evidencePhi": 0.15216704066581863, "agentGivenWorld": 34.909909909909906, "worldGivenAgent": 43.78531073446328 }, { "label": "Qwen3.6-Plus", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 33.49609375, "worldSem": 42.48046875, "dualSem": 13.96484375, "agentEvi": 14.74609375, "worldEvi": 5.95703125, "dualEvi": 1.46484375, "independentSem": 14.229297637939453, "independentEvi": 0.8784294128417969, "semanticPhi": -0.011335142330074302, "evidencePhi": 0.06987645056047806, "agentGivenWorld": 32.87356321839081, "worldGivenAgent": 41.690962099125365 }, { "label": "Qwen3.6-Flash", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 28.7109375, "worldSem": 56.73828125, "dualSem": 16.015625, "agentEvi": 19.23828125, "worldEvi": 18.5546875, "dualEvi": 5.078125, "independentSem": 16.29009246826172, "independentEvi": 3.5696029663085938, "semanticPhi": -0.012245196678764222, "evidencePhi": 0.09844776873833015, "agentGivenWorld": 28.227194492254732, "worldGivenAgent": 55.78231292517006 }, { "label": "Qwen3.5-Plus", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 29.00390625, "worldSem": 48.92578125, "dualSem": 14.6484375, "agentEvi": 12.3046875, "worldEvi": 8.30078125, "dualEvi": 1.07421875, "independentSem": 14.190387725830078, "independentEvi": 1.0213851928710938, "semanticPhi": 0.02019284209554284, "evidencePhi": 0.005829671254932969, "agentGivenWorld": 29.94011976047904, "worldGivenAgent": 50.505050505050505 }, { "label": "Qwen3.5-Flash", "groupId": "proprietary", "pair": "action_observation", "n": 1024, "agentSem": 28.90625, "worldSem": 54.4921875, "dualSem": 15.91796875, "agentEvi": 15.8203125, "worldEvi": 8.88671875, "dualEvi": 2.05078125, "independentSem": 15.75164794921875, "independentEvi": 1.4059066772460938, "semanticPhi": 0.007367580293718022, "evidencePhi": 0.06210155976544081, "agentGivenWorld": 29.211469534050178, "worldGivenAgent": 55.067567567567565 }, { "label": "GLM-5.3-Flash", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 35.15625, "worldSem": 57.421875, "dualSem": 20.5078125, "agentEvi": 45.41015625, "worldEvi": 33.0078125, "dualEvi": 20.5078125, "independentSem": 20.1873779296875, "independentEvi": 14.988899230957031, "semanticPhi": 0.013572882194152258, "evidencePhi": 0.23572231303851163, "agentGivenWorld": 35.714285714285715, "worldGivenAgent": 58.333333333333336 }, { "label": "GLM-4.6V", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 27.05078125, "worldSem": 44.23828125, "dualSem": 12.20703125, "agentEvi": 44.921875, "worldEvi": 10.15625, "dualEvi": 5.37109375, "independentSem": 11.966800689697266, "independentEvi": 4.5623779296875, "semanticPhi": 0.010888318769985387, "evidencePhi": 0.05382286369772553, "agentGivenWorld": 27.593818984547465, "worldGivenAgent": 45.12635379061371 }, { "label": "GLM-4.5V", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 29.00390625, "worldSem": 39.6484375, "dualSem": 11.328125, "agentEvi": 23.4375, "worldEvi": 17.7734375, "dualEvi": 6.640625, "independentSem": 11.499595642089844, "independentEvi": 4.1656494140625, "semanticPhi": -0.007724795711461524, "evidencePhi": 0.15283240263666184, "agentGivenWorld": 28.57142857142857, "worldGivenAgent": 39.05723905723906 }, { "label": "Intern-S1-Pro", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 26.171875, "worldSem": 30.2734375, "dualSem": 7.03125, "agentEvi": 10.546875, "worldEvi": 3.22265625, "dualEvi": 0.390625, "independentSem": 7.923126220703125, "independentEvi": 0.3398895263671875, "semanticPhi": -0.04416174753014924, "evidencePhi": 0.009353156917289036, "agentGivenWorld": 23.225806451612904, "worldGivenAgent": 26.865671641791046 }, { "label": "InternVL 3.5-241B-A28B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 26.07421875, "worldSem": 41.796875, "dualSem": 11.03515625, "agentEvi": 17.48046875, "worldEvi": 5.17578125, "dualEvi": 1.171875, "independentSem": 10.898208618164062, "independentEvi": 0.9047508239746094, "semanticPhi": 0.006324203775215169, "evidencePhi": 0.031747584595787186, "agentGivenWorld": 26.401869158878505, "worldGivenAgent": 42.32209737827715 }, { "label": "InternVL 3.5-30B-A3B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 24.0234375, "worldSem": 41.30859375, "dualSem": 8.88671875, "agentEvi": 7.03125, "worldEvi": 1.26953125, "dualEvi": 0.09765625, "independentSem": 9.923744201660156, "independentEvi": 0.089263916015625, "semanticPhi": -0.04929746154886118, "evidencePhi": 0.002931910412030588, "agentGivenWorld": 21.513002364066196, "worldGivenAgent": 36.99186991869919 }, { "label": "InternVL 3.5-14B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 31.93359375, "worldSem": 41.30859375, "dualSem": 13.4765625, "agentEvi": 7.51953125, "worldEvi": 4.98046875, "dualEvi": 0.48828125, "independentSem": 13.19131851196289, "independentEvi": 0.3745079040527344, "semanticPhi": 0.012425638885196245, "evidencePhi": 0.01983255116615063, "agentGivenWorld": 32.62411347517731, "worldGivenAgent": 42.201834862385326 }, { "label": "InternVL 3.5-8B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 24.51171875, "worldSem": 30.76171875, "dualSem": 7.8125, "agentEvi": 9.47265625, "worldEvi": 2.5390625, "dualEvi": 0.390625, "independentSem": 7.540225982666016, "independentEvi": 0.24051666259765625, "semanticPhi": 0.013715167325998373, "evidencePhi": 0.03258569957402895, "agentGivenWorld": 25.396825396825395, "worldGivenAgent": 31.872509960159363 }, { "label": "InternVL 3.5-4B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 26.3671875, "worldSem": 36.71875, "dualSem": 9.9609375, "agentEvi": 12.01171875, "worldEvi": 0.9765625, "dualEvi": 0, "independentSem": 9.68170166015625, "independentEvi": 0.11730194091796875, "semanticPhi": 0.01314686162821954, "evidencePhi": -0.036691982924949774, "agentGivenWorld": 27.127659574468083, "worldGivenAgent": 37.77777777777778 }, { "label": "Kimi K2.5", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 32.71484375, "worldSem": 30.078125, "dualSem": 9.66796875, "agentEvi": 18.45703125, "worldEvi": 4.6875, "dualEvi": 0.87890625, "independentSem": 9.840011596679688, "independentEvi": 0.86517333984375, "semanticPhi": -0.007995997493894711, "evidencePhi": 0.0016747223828233898, "agentGivenWorld": 32.142857142857146, "worldGivenAgent": 29.55223880597015 }, { "label": "Kimi K2.6", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 32.32421875, "worldSem": 28.02734375, "dualSem": 9.1796875, "agentEvi": 12.20703125, "worldEvi": 10.83984375, "dualEvi": 2.83203125, "independentSem": 9.059619903564453, "independentEvi": 1.3232231140136719, "semanticPhi": 0.005715713130881149, "evidencePhi": 0.14825255951576038, "agentGivenWorld": 32.752613240418114, "worldGivenAgent": 28.3987915407855 }, { "label": "MiMo-V2.5", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 27.34375, "worldSem": 49.70703125, "dualSem": 14.55078125, "agentEvi": 43.45703125, "worldEvi": 27.83203125, "dualEvi": 19.140625, "independentSem": 13.591766357421875, "independentEvi": 12.094974517822266, "semanticPhi": 0.04303256917395575, "evidencePhi": 0.31714441794996384, "agentGivenWorld": 29.273084479371313, "worldGivenAgent": 53.214285714285715 }, { "label": "Qwen3.8-27B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 28.80859375, "worldSem": 49.4140625, "dualSem": 14.74609375, "agentEvi": 16.9921875, "worldEvi": 21.875, "dualEvi": 6.25, "independentSem": 14.235496520996094, "independentEvi": 3.717041015625, "semanticPhi": 0.022550878050188353, "evidencePhi": 0.16314545558893145, "agentGivenWorld": 29.841897233201582, "worldGivenAgent": 51.186440677966104 }, { "label": "Qwen3.6-27B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 36.42578125, "worldSem": 53.41796875, "dualSem": 19.3359375, "agentEvi": 13.18359375, "worldEvi": 19.53125, "dualEvi": 4.1015625, "independentSem": 19.45791244506836, "independentEvi": 2.574920654296875, "semanticPhi": -0.005081275958473602, "evidencePhi": 0.11382579891998335, "agentGivenWorld": 36.19744058500914, "worldGivenAgent": 53.08310991957105 }, { "label": "Qwen3.5-397B-A17B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 35.83984375, "worldSem": 46.19140625, "dualSem": 16.9921875, "agentEvi": 13.4765625, "worldEvi": 4.39453125, "dualEvi": 1.26953125, "independentSem": 16.554927825927734, "independentEvi": 0.5922317504882812, "semanticPhi": 0.018290149414874342, "evidencePhi": 0.09676686272495105, "agentGivenWorld": 36.78646934460888, "worldGivenAgent": 47.41144414168937 }, { "label": "Qwen3.5-122B-A10B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 37.79296875, "worldSem": 49.0234375, "dualSem": 17.96875, "agentEvi": 25.9765625, "worldEvi": 6.8359375, "dualEvi": 1.85546875, "independentSem": 18.52741241455078, "independentEvi": 1.7757415771484375, "semanticPhi": -0.02304820237383938, "evidencePhi": 0.007204563092353106, "agentGivenWorld": 36.65338645418327, "worldGivenAgent": 47.54521963824289 }, { "label": "Qwen3.5-35B-A3B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 27.44140625, "worldSem": 57.51953125, "dualSem": 15.72265625, "agentEvi": 0.5859375, "worldEvi": 7.2265625, "dualEvi": 0, "independentSem": 15.784168243408203, "independentEvi": 0.0423431396484375, "semanticPhi": -0.0027887518534524362, "evidencePhi": -0.021426724886095677, "agentGivenWorld": 27.33446519524618, "worldGivenAgent": 57.29537366548043 }, { "label": "Qwen3.5-27B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 37.109375, "worldSem": 50.5859375, "dualSem": 18.1640625, "agentEvi": 22.75390625, "worldEvi": 7.51953125, "dualEvi": 2.34375, "independentSem": 18.772125244140625, "independentEvi": 1.7109870910644531, "semanticPhi": -0.025175229487829142, "evidencePhi": 0.05723403606720468, "agentGivenWorld": 35.907335907335906, "worldGivenAgent": 48.94736842105264 }, { "label": "Qwen3.5-9B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 29.00390625, "worldSem": 52.24609375, "dualSem": 15.8203125, "agentEvi": 22.94921875, "worldEvi": 11.5234375, "dualEvi": 3.22265625, "independentSem": 15.15340805053711, "independentEvi": 2.6445388793945312, "semanticPhi": 0.029422988198728465, "evidencePhi": 0.043056467584929314, "agentGivenWorld": 30.2803738317757, "worldGivenAgent": 54.54545454545454 }, { "label": "Qwen3.5-4B", "groupId": "open", "pair": "action_observation", "n": 1024, "agentSem": 30.17578125, "worldSem": 47.4609375, "dualSem": 15.4296875, "agentEvi": 12.40234375, "worldEvi": 6.34765625, "dualEvi": 1.26953125, "independentSem": 14.321708679199219, "independentEvi": 0.7872581481933594, "semanticPhi": 0.04833812929909345, "evidencePhi": 0.06001072723033859, "agentGivenWorld": 32.510288065843625, "worldGivenAgent": 51.1326860841424 }, { "label": "SpaceOm", "groupId": "specialized", "pair": "action_observation", "n": 1024, "agentSem": 24.51171875, "worldSem": 32.8125, "dualSem": 7.6171875, "agentEvi": 4.19921875, "worldEvi": 1.7578125, "dualEvi": 0.09765625, "independentSem": 8.04290771484375, "independentEvi": 0.07381439208984375, "semanticPhi": -0.02107820967916226, "evidencePhi": 0.009045571988516646, "agentGivenWorld": 23.214285714285715, "worldGivenAgent": 31.07569721115538 }, { "label": "SpaceR", "groupId": "specialized", "pair": "action_observation", "n": 1024, "agentSem": 24.0234375, "worldSem": 48.828125, "dualSem": 11.23046875, "agentEvi": 1.07421875, "worldEvi": 2.34375, "dualEvi": 0, "independentSem": 11.730194091796875, "independentEvi": 0.025177001953125, "semanticPhi": -0.023400400436080077, "evidencePhi": -0.016143483001983823, "agentGivenWorld": 23, "worldGivenAgent": 46.7479674796748 }, { "label": "SpaceThinker", "groupId": "specialized", "pair": "action_observation", "n": 1024, "agentSem": 25.390625, "worldSem": 34.27734375, "dualSem": 8.30078125, "agentEvi": 1.7578125, "worldEvi": 0.68359375, "dualEvi": 0, "independentSem": 8.703231811523438, "independentEvi": 0.01201629638671875, "semanticPhi": -0.019481303278025833, "evidencePhi": -0.01109751666155154, "agentGivenWorld": 24.216524216524217, "worldGivenAgent": 32.69230769230769 }, { "label": "ViLaSR", "groupId": "specialized", "pair": "action_observation", "n": 1024, "agentSem": 22.0703125, "worldSem": 49.70703125, "dualSem": 9.765625, "agentEvi": 1.953125, "worldEvi": 1.46484375, "dualEvi": 0.1953125, "independentSem": 10.970497131347656, "independentEvi": 0.0286102294921875, "semanticPhi": -0.058106230374650784, "evidencePhi": 0.10026938735528416, "agentGivenWorld": 19.646365422396855, "worldGivenAgent": 44.24778761061947 }, { "label": "Gemini 3.8 Flash", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 11.71875, "worldSem": 45.99609375, "dualSem": 6.93359375, "agentEvi": 15.625, "worldEvi": 30.46875, "dualEvi": 8.203125, "independentSem": 5.390167236328125, "independentEvi": 4.7607421875, "semanticPhi": 0.09628042801931026, "evidencePhi": 0.2059799372816829, "agentGivenWorld": 15.074309978768577, "worldGivenAgent": 59.166666666666664 }, { "label": "Gemini 3.1 Pro Preview", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 6.73828125, "worldSem": 33.49609375, "dualSem": 1.171875, "agentEvi": 6.54296875, "worldEvi": 26.7578125, "dualEvi": 2.05078125, "independentSem": 2.257061004638672, "independentEvi": 1.7507553100585938, "semanticPhi": -0.09171856479067658, "evidencePhi": 0.027406869693746047, "agentGivenWorld": 3.498542274052478, "worldGivenAgent": 17.391304347826086 }, { "label": "Gemini 3.1 Flash Lite", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 9.375, "worldSem": 52.83203125, "dualSem": 7.32421875, "agentEvi": 8.49609375, "worldEvi": 47.94921875, "dualEvi": 5.46875, "independentSem": 4.9530029296875, "independentEvi": 4.073810577392578, "semanticPhi": 0.16296306886789164, "evidencePhi": 0.10014320558685584, "agentGivenWorld": 13.863216266173753, "worldGivenAgent": 78.125 }, { "label": "Gemini 3 Flash", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 19.53125, "worldSem": 55.17578125, "dualSem": 11.42578125, "agentEvi": 24.21875, "worldEvi": 48.92578125, "dualEvi": 12.59765625, "independentSem": 10.776519775390625, "independentEvi": 11.849212646484375, "semanticPhi": 0.03293141384745911, "evidencePhi": 0.034948825552891645, "agentGivenWorld": 20.707964601769913, "worldGivenAgent": 58.5 }, { "label": "MiMo-V2-Omni", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 17.48046875, "worldSem": 59.375, "dualSem": 10.64453125, "agentEvi": 16.69921875, "worldEvi": 58.88671875, "dualEvi": 11.5234375, "independentSem": 10.3790283203125, "independentEvi": 9.833621978759766, "semanticPhi": 0.014233637661725652, "evidencePhi": 0.09208034405983039, "agentGivenWorld": 17.927631578947366, "worldGivenAgent": 60.893854748603346 }, { "label": "Muse Spark 1.3 Contributor", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 18.06640625, "worldSem": 47.8515625, "dualSem": 12.59765625, "agentEvi": 25.09765625, "worldEvi": 51.953125, "dualEvi": 16.2109375, "independentSem": 8.645057678222656, "independentEvi": 13.039016723632812, "semanticPhi": 0.20565871102450364, "evidencePhi": 0.14642648383527232, "agentGivenWorld": 26.3265306122449, "worldGivenAgent": 69.72972972972973 }, { "label": "Qwen3.7-Plus", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 19.04296875, "worldSem": 53.61328125, "dualSem": 13.96484375, "agentEvi": 18.9453125, "worldEvi": 62.3046875, "dualEvi": 11.5234375, "independentSem": 10.20956039428711, "independentEvi": 11.803817749023438, "semanticPhi": 0.19178519464716756, "evidencePhi": -0.014763979298159839, "agentGivenWorld": 26.04735883424408, "worldGivenAgent": 73.33333333333333 }, { "label": "Qwen3.6-Plus", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 16.9921875, "worldSem": 50.78125, "dualSem": 14.84375, "agentEvi": 12.3046875, "worldEvi": 57.12890625, "dualEvi": 8.49609375, "independentSem": 8.62884521484375, "independentEvi": 7.029533386230469, "semanticPhi": 0.3310040942703745, "evidencePhi": 0.09021239701306454, "agentGivenWorld": 29.230769230769234, "worldGivenAgent": 87.35632183908046 }, { "label": "Qwen3.6-Flash", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 13.8671875, "worldSem": 52.24609375, "dualSem": 11.5234375, "agentEvi": 12.5, "worldEvi": 58.59375, "dualEvi": 7.32421875, "independentSem": 7.245063781738281, "independentEvi": 7.32421875, "semanticPhi": 0.24783854209839645, "evidencePhi": 0, "agentGivenWorld": 22.05607476635514, "worldGivenAgent": 83.09859154929578 }, { "label": "Qwen3.5-Plus", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 19.04296875, "worldSem": 53.22265625, "dualSem": 14.35546875, "agentEvi": 13.96484375, "worldEvi": 59.5703125, "dualEvi": 9.08203125, "independentSem": 10.135173797607422, "independentEvi": 8.318901062011719, "semanticPhi": 0.21541807413680583, "evidencePhi": 0.04486188172414448, "agentGivenWorld": 26.972477064220186, "worldGivenAgent": 75.38461538461539 }, { "label": "Qwen3.5-Flash", "groupId": "proprietary", "pair": "behavior_visibility", "n": 1024, "agentSem": 13.0859375, "worldSem": 52.34375, "dualSem": 9.27734375, "agentEvi": 12.890625, "worldEvi": 65.0390625, "dualEvi": 9.47265625, "independentSem": 6.84967041015625, "independentEvi": 8.383941650390625, "semanticPhi": 0.14412869486035618, "evidencePhi": 0.06813432212030515, "agentGivenWorld": 17.723880597014926, "worldGivenAgent": 70.8955223880597 }, { "label": "GLM-5.3-Flash", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 15.625, "worldSem": 49.12109375, "dualSem": 11.81640625, "agentEvi": 16.796875, "worldEvi": 48.6328125, "dualEvi": 9.375, "independentSem": 7.6751708984375, "independentEvi": 8.168792724609375, "semanticPhi": 0.2281445555613117, "evidencePhi": 0.06455506052306492, "agentGivenWorld": 24.055666003976143, "worldGivenAgent": 75.625 }, { "label": "GLM-4.6V", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 4.39453125, "worldSem": 31.25, "dualSem": 0.09765625, "agentEvi": 2.1484375, "worldEvi": 24.90234375, "dualEvi": 0.48828125, "independentSem": 1.373291015625, "independentEvi": 0.5350112915039062, "semanticPhi": -0.13426639813413893, "evidencePhi": -0.00745276828501489, "agentGivenWorld": 0.3125, "worldGivenAgent": 2.2222222222222223 }, { "label": "InternVL 3.5-30B-A3B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 9.5703125, "worldSem": 43.9453125, "dualSem": 7.2265625, "agentEvi": 2.9296875, "worldEvi": 9.86328125, "dualEvi": 0.29296875, "independentSem": 4.2057037353515625, "independentEvi": 0.28896331787109375, "semanticPhi": 0.20689481170836113, "evidencePhi": 0.00079658831847932, "agentGivenWorld": 16.444444444444446, "worldGivenAgent": 75.51020408163265 }, { "label": "InternVL 3.5-14B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 5.46875, "worldSem": 54.4921875, "dualSem": 3.02734375, "agentEvi": 2.63671875, "worldEvi": 17.28515625, "dualEvi": 0.87890625, "independentSem": 2.98004150390625, "independentEvi": 0.4557609558105469, "semanticPhi": 0.004177725745500946, "evidencePhi": 0.0698444061513843, "agentGivenWorld": 5.555555555555555, "worldGivenAgent": 55.35714285714286 }, { "label": "InternVL 3.5-8B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 7.03125, "worldSem": 51.85546875, "dualSem": 6.4453125, "agentEvi": 1.953125, "worldEvi": 17.08984375, "dualEvi": 0.29296875, "independentSem": 3.646087646484375, "independentEvi": 0.3337860107421875, "semanticPhi": 0.21912011953358781, "evidencePhi": -0.007835902892669047, "agentGivenWorld": 12.429378531073446, "worldGivenAgent": 91.66666666666666 }, { "label": "InternVL 3.5-4B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 3.41796875, "worldSem": 34.5703125, "dualSem": 0.390625, "agentEvi": 2.05078125, "worldEvi": 24.4140625, "dualEvi": 0.48828125, "independentSem": 1.1816024780273438, "independentEvi": 0.5006790161132812, "semanticPhi": -0.09153618974945814, "evidencePhi": -0.002036304653550958, "agentGivenWorld": 1.1299435028248588, "worldGivenAgent": 11.428571428571429 }, { "label": "Kimi K2.5", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 17.67578125, "worldSem": 50.48828125, "dualSem": 11.5234375, "agentEvi": 17.578125, "worldEvi": 53.80859375, "dualEvi": 10.15625, "independentSem": 8.924198150634766, "independentEvi": 9.458541870117188, "semanticPhi": 0.13628368260847504, "evidencePhi": 0.036767140199971085, "agentGivenWorld": 22.823984526112184, "worldGivenAgent": 65.19337016574586 }, { "label": "Kimi K2.6", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 16.796875, "worldSem": 39.94140625, "dualSem": 8.49609375, "agentEvi": 16.40625, "worldEvi": 53.90625, "dualEvi": 7.8125, "independentSem": 6.7089080810546875, "independentEvi": 8.843994140625, "semanticPhi": 0.0976082112000727, "evidencePhi": -0.05587719764201875, "agentGivenWorld": 21.271393643031786, "worldGivenAgent": 50.58139534883721 }, { "label": "MiMo-V2.5", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 16.2109375, "worldSem": 58.49609375, "dualSem": 11.9140625, "agentEvi": 17.08984375, "worldEvi": 60.15625, "dualEvi": 9.9609375, "independentSem": 9.482765197753906, "independentEvi": 10.280609130859375, "semanticPhi": 0.13388515240931737, "evidencePhi": -0.017346453764035322, "agentGivenWorld": 20.36727879799666, "worldGivenAgent": 73.49397590361446 }, { "label": "Qwen3.8-27B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 10.15625, "worldSem": 43.1640625, "dualSem": 8.88671875, "agentEvi": 4.78515625, "worldEvi": 17.08984375, "dualEvi": 0.48828125, "independentSem": 4.38385009765625, "independentEvi": 0.8177757263183594, "semanticPhi": 0.30095806215951154, "evidencePhi": -0.04100858973579908, "agentGivenWorld": 20.588235294117645, "worldGivenAgent": 87.5 }, { "label": "Qwen3.6-27B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 15.33203125, "worldSem": 52.734375, "dualSem": 13.37890625, "agentEvi": 13.4765625, "worldEvi": 47.94921875, "dualEvi": 7.71484375, "independentSem": 8.085250854492188, "independentEvi": 6.461906433105469, "semanticPhi": 0.29429077178891744, "evidencePhi": 0.07344605995045414, "agentGivenWorld": 25.37037037037037, "worldGivenAgent": 87.26114649681529 }, { "label": "Qwen3.5-397B-A17B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 11.9140625, "worldSem": 40.4296875, "dualSem": 5.6640625, "agentEvi": 5.46875, "worldEvi": 26.26953125, "dualEvi": 1.85546875, "independentSem": 4.8168182373046875, "independentEvi": 1.436614990234375, "semanticPhi": 0.05329178629973303, "evidencePhi": 0.041858245756256705, "agentGivenWorld": 14.009661835748794, "worldGivenAgent": 47.540983606557376 }, { "label": "Qwen3.5-122B-A10B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 11.62109375, "worldSem": 48.4375, "dualSem": 5.37109375, "agentEvi": 11.42578125, "worldEvi": 54.296875, "dualEvi": 6.54296875, "independentSem": 5.62896728515625, "independentEvi": 6.2038421630859375, "semanticPhi": -0.016100935767778757, "evidencePhi": 0.021399560577929456, "agentGivenWorld": 11.088709677419354, "worldGivenAgent": 46.21848739495798 }, { "label": "Qwen3.5-35B-A3B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 14.35546875, "worldSem": 54.1015625, "dualSem": 8.88671875, "agentEvi": 13.96484375, "worldEvi": 56.93359375, "dualEvi": 8.984375, "independentSem": 7.766532897949219, "independentEvi": 7.950687408447266, "semanticPhi": 0.06411028700600056, "evidencePhi": 0.06022539696236516, "agentGivenWorld": 16.425992779783392, "worldGivenAgent": 61.904761904761905 }, { "label": "Qwen3.5-27B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 15.8203125, "worldSem": 51.3671875, "dualSem": 11.23046875, "agentEvi": 15.72265625, "worldEvi": 58.0078125, "dualEvi": 9.66796875, "independentSem": 8.126449584960938, "independentEvi": 9.120368957519531, "semanticPhi": 0.17017886533681043, "evidencePhi": 0.03048017120010676, "agentGivenWorld": 21.863117870722434, "worldGivenAgent": 70.98765432098766 }, { "label": "Qwen3.5-9B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 14.16015625, "worldSem": 50.68359375, "dualSem": 8.0078125, "agentEvi": 13.8671875, "worldEvi": 40.8203125, "dualEvi": 5.95703125, "independentSem": 7.176876068115234, "independentEvi": 5.6606292724609375, "semanticPhi": 0.04767161965023869, "evidencePhi": 0.017449303335224108, "agentGivenWorld": 15.79961464354528, "worldGivenAgent": 56.55172413793104 }, { "label": "Qwen3.5-4B", "groupId": "open", "pair": "behavior_visibility", "n": 1024, "agentSem": 7.12890625, "worldSem": 33.88671875, "dualSem": 0.5859375, "agentEvi": 0.78125, "worldEvi": 57.32421875, "dualEvi": 0.390625, "independentSem": 2.415752410888672, "independentEvi": 0.447845458984375, "semanticPhi": -0.15024371557186272, "evidencePhi": -0.013140129150683586, "agentGivenWorld": 1.729106628242075, "worldGivenAgent": 8.21917808219178 }, { "label": "SpaceOm", "groupId": "specialized", "pair": "behavior_visibility", "n": 1024, "agentSem": 7.12890625, "worldSem": 32.32421875, "dualSem": 0.29296875, "agentEvi": 1.85546875, "worldEvi": 25.29296875, "dualEvi": 0, "independentSem": 2.304363250732422, "independentEvi": 0.4693031311035156, "semanticPhi": -0.1671340237594331, "evidencePhi": -0.08000422711818546, "agentGivenWorld": 0.906344410876133, "worldGivenAgent": 4.10958904109589 }, { "label": "SpaceR", "groupId": "specialized", "pair": "behavior_visibility", "n": 1024, "agentSem": 5.37109375, "worldSem": 33.69140625, "dualSem": 0.390625, "agentEvi": 2.05078125, "worldEvi": 23.046875, "dualEvi": 0, "independentSem": 1.8095970153808594, "independentEvi": 0.4726409912109375, "semanticPhi": -0.13316376811463917, "evidencePhi": -0.0791866688021091, "agentGivenWorld": 1.1594202898550725, "worldGivenAgent": 7.2727272727272725 }, { "label": "SpaceThinker", "groupId": "specialized", "pair": "behavior_visibility", "n": 1024, "agentSem": 7.91015625, "worldSem": 33.69140625, "dualSem": 0.87890625, "agentEvi": 2.05078125, "worldEvi": 20.21484375, "dualEvi": 0, "independentSem": 2.6650428771972656, "independentEvi": 0.4145622253417969, "semanticPhi": -0.1400141083924929, "evidencePhi": -0.07283385971615856, "agentGivenWorld": 2.608695652173913, "worldGivenAgent": 11.11111111111111 }, { "label": "ViLaSR", "groupId": "specialized", "pair": "behavior_visibility", "n": 1024, "agentSem": 7.03125, "worldSem": 35.9375, "dualSem": 1.5625, "agentEvi": 0.390625, "worldEvi": 15.0390625, "dualEvi": 0, "independentSem": 2.52685546875, "independentEvi": 0.058746337890625, "semanticPhi": -0.07860976708700325, "evidencePhi": -0.02634696799558326, "agentGivenWorld": 4.3478260869565215, "worldGivenAgent": 22.22222222222222 } ], "capabilitySummaries": [ { "id": "position", "summaries": [ { "metric": "Sem", "n": 32, "agent": 31.0272216796875, "world": 47.454833984375, "dual": 14.544677734375, "independent": 15.158998966217041, "agentCorrelation": { "n": 32, "pearson": 0.8772670831598264, "spearman": 0.7175068744271311 }, "worldCorrelation": { "n": 32, "pearson": 0.7912533283034999, "spearman": 0.9184085229548714 } }, { "metric": "Evi", "n": 32, "agent": 24.9298095703125, "world": 11.48681640625, "dual": 6.134033203125, "independent": 4.203447699546814, "agentCorrelation": { "n": 32, "pearson": 0.7746057754645056, "spearman": 0.8319428764509649 }, "worldCorrelation": { "n": 32, "pearson": 0.9696486979606439, "spearman": 0.9638598422307834 } } ] }, { "id": "action_observation", "summaries": [ { "metric": "Sem", "n": 32, "agent": 32.94677734375, "world": 46.3592529296875, "dual": 15.911865234375, "independent": 15.820801258087158, "agentCorrelation": { "n": 32, "pearson": 0.9310118435263023, "spearman": 0.798056680649109 }, "worldCorrelation": { "n": 32, "pearson": 0.762247586558621, "spearman": 0.8117323692763704 } }, { "metric": "Evi", "n": 32, "agent": 21.636962890625, "world": 11.4410400390625, "dual": 5.2490234375, "independent": 3.904619812965393, "agentCorrelation": { "n": 32, "pearson": 0.8363847397064436, "spearman": 0.8631197891140784 }, "worldCorrelation": { "n": 32, "pearson": 0.928184889858024, "spearman": 0.9278904705675796 } } ] }, { "id": "behavior_visibility", "summaries": [ { "metric": "Sem", "n": 32, "agent": 12.158203125, "world": 46.2982177734375, "dual": 7.5042724609375, "independent": 5.917289853096008, "agentCorrelation": { "n": 32, "pearson": 0.91541228532598, "spearman": 0.8866678892352833 }, "worldCorrelation": { "n": 32, "pearson": 0.810824812232868, "spearman": 0.6986615445636929 } }, { "metric": "Evi", "n": 32, "agent": 10.3973388671875, "world": 41.24755859375, "dual": 5.7281494140625, "independent": 5.204644799232483, "agentCorrelation": { "n": 32, "pearson": 0.9760795586062702, "spearman": 0.9506937178540226 }, "worldCorrelation": { "n": 32, "pearson": 0.811795957290967, "spearman": 0.7678544985727068 } } ] } ] }