CheeseBench commited on
Commit
421750e
·
1 Parent(s): 1700c27

Rebuild leaderboard: exclude TOPDOWN_2D from text(ASCII) tier

Browse files
Files changed (1) hide show
  1. leaderboard.json +159 -225
leaderboard.json CHANGED
@@ -741,8 +741,7 @@
741
  "overall_by_view": {
742
  "ASCII_2D": 0.5264777777777777,
743
  "ASCII_2D_FPV": 0.3620333333333334,
744
- "ASCII_3D": 0.5337999999999998,
745
- "TOPDOWN_2D": 0.4590777777777778
746
  },
747
  "per_environment": {
748
  "MorrisWaterMaze": {
@@ -751,8 +750,7 @@
751
  "view_mode_scores": {
752
  "ASCII_2D": 0.3,
753
  "ASCII_2D_FPV": 0.95,
754
- "ASCII_3D": 0.7,
755
- "TOPDOWN_2D": 0.55
756
  }
757
  },
758
  "TMaze": {
@@ -761,8 +759,7 @@
761
  "view_mode_scores": {
762
  "ASCII_2D": 0.7,
763
  "ASCII_2D_FPV": 0.225,
764
- "ASCII_3D": 0.875,
765
- "TOPDOWN_2D": 0.625
766
  }
767
  },
768
  "BarnesMaze": {
@@ -771,8 +768,7 @@
771
  "view_mode_scores": {
772
  "ASCII_2D": 0.75,
773
  "ASCII_2D_FPV": 0.25,
774
- "ASCII_3D": 0.4375,
775
- "TOPDOWN_2D": 0.375
776
  }
777
  },
778
  "RadialArmMaze": {
@@ -781,8 +777,7 @@
781
  "view_mode_scores": {
782
  "ASCII_2D": 0.05,
783
  "ASCII_2D_FPV": 0.1,
784
- "ASCII_3D": 0.05,
785
- "TOPDOWN_2D": 0.0
786
  }
787
  },
788
  "OperantChamber": {
@@ -791,8 +786,7 @@
791
  "view_mode_scores": {
792
  "ASCII_2D": 0.84,
793
  "ASCII_2D_FPV": 0.28,
794
- "ASCII_3D": 0.84,
795
- "TOPDOWN_2D": 0.84
796
  }
797
  },
798
  "ShuttleBox": {
@@ -801,8 +795,7 @@
801
  "view_mode_scores": {
802
  "ASCII_2D": 0.625,
803
  "ASCII_2D_FPV": 0.8,
804
- "ASCII_3D": 0.3,
805
- "TOPDOWN_2D": 0.425
806
  }
807
  },
808
  "PlacePreference": {
@@ -811,8 +804,7 @@
811
  "view_mode_scores": {
812
  "ASCII_2D": 0.5833,
813
  "ASCII_2D_FPV": 0.0833,
814
- "ASCII_3D": 0.9167,
815
- "TOPDOWN_2D": 0.6667
816
  }
817
  },
818
  "StarMaze": {
@@ -821,8 +813,7 @@
821
  "view_mode_scores": {
822
  "ASCII_2D": 0.35,
823
  "ASCII_2D_FPV": 0.05,
824
- "ASCII_3D": 0.175,
825
- "TOPDOWN_2D": 0.2
826
  }
827
  },
828
  "DNMSTask": {
@@ -831,17 +822,15 @@
831
  "view_mode_scores": {
832
  "ASCII_2D": 0.54,
833
  "ASCII_2D_FPV": 0.52,
834
- "ASCII_3D": 0.51,
835
- "TOPDOWN_2D": 0.45
836
  }
837
  }
838
  },
839
- "total_trials": 1352,
840
  "view_modes": [
841
  "ASCII_2D",
842
  "ASCII_2D_FPV",
843
- "ASCII_3D",
844
- "TOPDOWN_2D"
845
  ]
846
  },
847
  {
@@ -849,12 +838,11 @@
849
  "model_id": "qwen2.5vl-32b",
850
  "modality": "text (ASCII)",
851
  "source": "open-weights/vLLM",
852
- "overall": 0.674911111111111,
853
  "overall_by_view": {
854
  "ASCII_2D": 0.4800888888888889,
855
  "ASCII_2D_FPV": 0.5351888888888889,
856
- "ASCII_3D": 0.43472222222222223,
857
- "TOPDOWN_2D": 0.4143555555555556
858
  },
859
  "per_environment": {
860
  "MorrisWaterMaze": {
@@ -863,8 +851,7 @@
863
  "view_mode_scores": {
864
  "ASCII_2D": 0.95,
865
  "ASCII_2D_FPV": 0.45,
866
- "ASCII_3D": 0.45,
867
- "TOPDOWN_2D": 0.45
868
  }
869
  },
870
  "TMaze": {
@@ -873,8 +860,7 @@
873
  "view_mode_scores": {
874
  "ASCII_2D": 0.125,
875
  "ASCII_2D_FPV": 0.825,
876
- "ASCII_3D": 0.275,
877
- "TOPDOWN_2D": 0.225
878
  }
879
  },
880
  "BarnesMaze": {
@@ -883,8 +869,7 @@
883
  "view_mode_scores": {
884
  "ASCII_2D": 0.6875,
885
  "ASCII_2D_FPV": 0.5,
886
- "ASCII_3D": 0.4375,
887
- "TOPDOWN_2D": 0.3125
888
  }
889
  },
890
  "RadialArmMaze": {
@@ -893,8 +878,7 @@
893
  "view_mode_scores": {
894
  "ASCII_2D": 0.0,
895
  "ASCII_2D_FPV": 0.0,
896
- "ASCII_3D": 0.0,
897
- "TOPDOWN_2D": 0.0
898
  }
899
  },
900
  "OperantChamber": {
@@ -903,8 +887,7 @@
903
  "view_mode_scores": {
904
  "ASCII_2D": 0.28,
905
  "ASCII_2D_FPV": 1.0,
906
- "ASCII_3D": 0.76,
907
- "TOPDOWN_2D": 0.52
908
  }
909
  },
910
  "ShuttleBox": {
@@ -913,18 +896,16 @@
913
  "view_mode_scores": {
914
  "ASCII_2D": 0.95,
915
  "ASCII_2D_FPV": 0.825,
916
- "ASCII_3D": 0.85,
917
- "TOPDOWN_2D": 0.6
918
  }
919
  },
920
  "PlacePreference": {
921
- "success_rate": 0.9167,
922
- "best_view_mode": "TOPDOWN_2D",
923
  "view_mode_scores": {
924
  "ASCII_2D": 0.5833,
925
  "ASCII_2D_FPV": 0.6667,
926
- "ASCII_3D": 0.5,
927
- "TOPDOWN_2D": 0.9167
928
  }
929
  },
930
  "StarMaze": {
@@ -933,8 +914,7 @@
933
  "view_mode_scores": {
934
  "ASCII_2D": 0.225,
935
  "ASCII_2D_FPV": 0.15,
936
- "ASCII_3D": 0.2,
937
- "TOPDOWN_2D": 0.225
938
  }
939
  },
940
  "DNMSTask": {
@@ -943,17 +923,15 @@
943
  "view_mode_scores": {
944
  "ASCII_2D": 0.52,
945
  "ASCII_2D_FPV": 0.4,
946
- "ASCII_3D": 0.44,
947
- "TOPDOWN_2D": 0.48
948
  }
949
  }
950
  },
951
- "total_trials": 1352,
952
  "view_modes": [
953
  "ASCII_2D",
954
  "ASCII_2D_FPV",
955
- "ASCII_3D",
956
- "TOPDOWN_2D"
957
  ]
958
  },
959
  {
@@ -961,12 +939,11 @@
961
  "model_id": "qwen2.5vl-72b",
962
  "modality": "text (ASCII)",
963
  "source": "open-weights/vLLM",
964
- "overall": 0.6001888888888889,
965
  "overall_by_view": {
966
  "ASCII_2D": 0.49342222222222226,
967
  "ASCII_2D_FPV": 0.49518888888888885,
968
- "ASCII_3D": 0.47213333333333324,
969
- "TOPDOWN_2D": 0.5161111111111111
970
  },
971
  "per_environment": {
972
  "MorrisWaterMaze": {
@@ -975,8 +952,7 @@
975
  "view_mode_scores": {
976
  "ASCII_2D": 0.8,
977
  "ASCII_2D_FPV": 0.6,
978
- "ASCII_3D": 0.85,
979
- "TOPDOWN_2D": 0.7
980
  }
981
  },
982
  "TMaze": {
@@ -985,18 +961,16 @@
985
  "view_mode_scores": {
986
  "ASCII_2D": 0.625,
987
  "ASCII_2D_FPV": 0.725,
988
- "ASCII_3D": 0.425,
989
- "TOPDOWN_2D": 0.6
990
  }
991
  },
992
  "BarnesMaze": {
993
- "success_rate": 0.5,
994
- "best_view_mode": "TOPDOWN_2D",
995
  "view_mode_scores": {
996
  "ASCII_2D": 0.4375,
997
  "ASCII_2D_FPV": 0.375,
998
- "ASCII_3D": 0.0625,
999
- "TOPDOWN_2D": 0.5
1000
  }
1001
  },
1002
  "RadialArmMaze": {
@@ -1005,8 +979,7 @@
1005
  "view_mode_scores": {
1006
  "ASCII_2D": 0.0,
1007
  "ASCII_2D_FPV": 0.0,
1008
- "ASCII_3D": 0.0,
1009
- "TOPDOWN_2D": 0.0
1010
  }
1011
  },
1012
  "OperantChamber": {
@@ -1015,18 +988,16 @@
1015
  "view_mode_scores": {
1016
  "ASCII_2D": 0.94,
1017
  "ASCII_2D_FPV": 0.98,
1018
- "ASCII_3D": 0.92,
1019
- "TOPDOWN_2D": 0.94
1020
  }
1021
  },
1022
  "ShuttleBox": {
1023
- "success_rate": 0.775,
1024
- "best_view_mode": "TOPDOWN_2D",
1025
  "view_mode_scores": {
1026
  "ASCII_2D": 0.35,
1027
  "ASCII_2D_FPV": 0.6,
1028
- "ASCII_3D": 0.7,
1029
- "TOPDOWN_2D": 0.775
1030
  }
1031
  },
1032
  "PlacePreference": {
@@ -1035,8 +1006,7 @@
1035
  "view_mode_scores": {
1036
  "ASCII_2D": 0.5833,
1037
  "ASCII_2D_FPV": 0.6667,
1038
- "ASCII_3D": 0.4167,
1039
- "TOPDOWN_2D": 0.5
1040
  }
1041
  },
1042
  "StarMaze": {
@@ -1045,8 +1015,7 @@
1045
  "view_mode_scores": {
1046
  "ASCII_2D": 0.225,
1047
  "ASCII_2D_FPV": 0.05,
1048
- "ASCII_3D": 0.425,
1049
- "TOPDOWN_2D": 0.2
1050
  }
1051
  },
1052
  "DNMSTask": {
@@ -1055,17 +1024,15 @@
1055
  "view_mode_scores": {
1056
  "ASCII_2D": 0.48,
1057
  "ASCII_2D_FPV": 0.46,
1058
- "ASCII_3D": 0.45,
1059
- "TOPDOWN_2D": 0.43
1060
  }
1061
  }
1062
  },
1063
- "total_trials": 1352,
1064
  "view_modes": [
1065
  "ASCII_2D",
1066
  "ASCII_2D_FPV",
1067
- "ASCII_3D",
1068
- "TOPDOWN_2D"
1069
  ]
1070
  },
1071
  {
@@ -1174,12 +1141,11 @@
1174
  "model_id": "qwen2.5vl-3b",
1175
  "modality": "text (ASCII)",
1176
  "source": "open-weights/vLLM",
1177
- "overall": 0.5162999999999999,
1178
  "overall_by_view": {
1179
  "ASCII_2D": 0.25869999999999993,
1180
  "ASCII_2D_FPV": 0.22425555555555554,
1181
- "ASCII_3D": 0.4126888888888889,
1182
- "TOPDOWN_2D": 0.24305555555555555
1183
  },
1184
  "per_environment": {
1185
  "MorrisWaterMaze": {
@@ -1188,8 +1154,7 @@
1188
  "view_mode_scores": {
1189
  "ASCII_2D": 0.45,
1190
  "ASCII_2D_FPV": 0.55,
1191
- "ASCII_3D": 0.95,
1192
- "TOPDOWN_2D": 0.95
1193
  }
1194
  },
1195
  "TMaze": {
@@ -1198,8 +1163,7 @@
1198
  "view_mode_scores": {
1199
  "ASCII_2D": 0.125,
1200
  "ASCII_2D_FPV": 0.1,
1201
- "ASCII_3D": 1.0,
1202
- "TOPDOWN_2D": 0.1
1203
  }
1204
  },
1205
  "BarnesMaze": {
@@ -1208,8 +1172,7 @@
1208
  "view_mode_scores": {
1209
  "ASCII_2D": 0.375,
1210
  "ASCII_2D_FPV": 0.125,
1211
- "ASCII_3D": 0.0625,
1212
- "TOPDOWN_2D": 0.0625
1213
  }
1214
  },
1215
  "RadialArmMaze": {
@@ -1218,8 +1181,7 @@
1218
  "view_mode_scores": {
1219
  "ASCII_2D": 0.0,
1220
  "ASCII_2D_FPV": 0.0,
1221
- "ASCII_3D": 0.0,
1222
- "TOPDOWN_2D": 0.0
1223
  }
1224
  },
1225
  "OperantChamber": {
@@ -1228,8 +1190,7 @@
1228
  "view_mode_scores": {
1229
  "ASCII_2D": 0.14,
1230
  "ASCII_2D_FPV": 0.54,
1231
- "ASCII_3D": 0.04,
1232
- "TOPDOWN_2D": 0.06
1233
  }
1234
  },
1235
  "ShuttleBox": {
@@ -1238,8 +1199,7 @@
1238
  "view_mode_scores": {
1239
  "ASCII_2D": 0.525,
1240
  "ASCII_2D_FPV": 0.225,
1241
- "ASCII_3D": 0.675,
1242
- "TOPDOWN_2D": 0.1
1243
  }
1244
  },
1245
  "PlacePreference": {
@@ -1248,8 +1208,7 @@
1248
  "view_mode_scores": {
1249
  "ASCII_2D": 0.3333,
1250
  "ASCII_2D_FPV": 0.3333,
1251
- "ASCII_3D": 0.6667,
1252
- "TOPDOWN_2D": 0.5
1253
  }
1254
  },
1255
  "StarMaze": {
@@ -1258,27 +1217,24 @@
1258
  "view_mode_scores": {
1259
  "ASCII_2D": 0.0,
1260
  "ASCII_2D_FPV": 0.025,
1261
- "ASCII_3D": 0.05,
1262
- "TOPDOWN_2D": 0.025
1263
  }
1264
  },
1265
  "DNMSTask": {
1266
- "success_rate": 0.39,
1267
- "best_view_mode": "TOPDOWN_2D",
1268
  "view_mode_scores": {
1269
  "ASCII_2D": 0.38,
1270
  "ASCII_2D_FPV": 0.12,
1271
- "ASCII_3D": 0.27,
1272
- "TOPDOWN_2D": 0.39
1273
  }
1274
  }
1275
  },
1276
- "total_trials": 1352,
1277
  "view_modes": [
1278
  "ASCII_2D",
1279
  "ASCII_2D_FPV",
1280
- "ASCII_3D",
1281
- "TOPDOWN_2D"
1282
  ]
1283
  },
1284
  {
@@ -1365,12 +1321,11 @@
1365
  "model_id": "phi-4-mm-14b",
1366
  "modality": "text (ASCII)",
1367
  "source": "open-weights/vLLM",
1368
- "overall": 0.48869999999999997,
1369
  "overall_by_view": {
1370
  "ASCII_2D": 0.37147777777777774,
1371
  "ASCII_2D_FPV": 0.32147777777777775,
1372
- "ASCII_3D": 0.24286666666666668,
1373
- "TOPDOWN_2D": 0.09925555555555556
1374
  },
1375
  "per_environment": {
1376
  "MorrisWaterMaze": {
@@ -1379,8 +1334,7 @@
1379
  "view_mode_scores": {
1380
  "ASCII_2D": 0.85,
1381
  "ASCII_2D_FPV": 0.1,
1382
- "ASCII_3D": 0.15,
1383
- "TOPDOWN_2D": 0.0
1384
  }
1385
  },
1386
  "TMaze": {
@@ -1389,18 +1343,16 @@
1389
  "view_mode_scores": {
1390
  "ASCII_2D": 0.575,
1391
  "ASCII_2D_FPV": 0.5,
1392
- "ASCII_3D": 0.325,
1393
- "TOPDOWN_2D": 0.0
1394
  }
1395
  },
1396
  "BarnesMaze": {
1397
- "success_rate": 0.375,
1398
- "best_view_mode": "TOPDOWN_2D",
1399
  "view_mode_scores": {
1400
  "ASCII_2D": 0.25,
1401
  "ASCII_2D_FPV": 0.125,
1402
- "ASCII_3D": 0.1875,
1403
- "TOPDOWN_2D": 0.375
1404
  }
1405
  },
1406
  "RadialArmMaze": {
@@ -1409,8 +1361,7 @@
1409
  "view_mode_scores": {
1410
  "ASCII_2D": 0.0,
1411
  "ASCII_2D_FPV": 0.0,
1412
- "ASCII_3D": 0.0,
1413
- "TOPDOWN_2D": 0.0
1414
  }
1415
  },
1416
  "OperantChamber": {
@@ -1419,8 +1370,7 @@
1419
  "view_mode_scores": {
1420
  "ASCII_2D": 0.52,
1421
  "ASCII_2D_FPV": 0.42,
1422
- "ASCII_3D": 0.6,
1423
- "TOPDOWN_2D": 0.16
1424
  }
1425
  },
1426
  "ShuttleBox": {
@@ -1429,8 +1379,7 @@
1429
  "view_mode_scores": {
1430
  "ASCII_2D": 0.5,
1431
  "ASCII_2D_FPV": 0.375,
1432
- "ASCII_3D": 0.3,
1433
- "TOPDOWN_2D": 0.025
1434
  }
1435
  },
1436
  "PlacePreference": {
@@ -1439,8 +1388,7 @@
1439
  "view_mode_scores": {
1440
  "ASCII_2D": 0.0833,
1441
  "ASCII_2D_FPV": 0.8333,
1442
- "ASCII_3D": 0.3333,
1443
- "TOPDOWN_2D": 0.3333
1444
  }
1445
  },
1446
  "StarMaze": {
@@ -1449,8 +1397,7 @@
1449
  "view_mode_scores": {
1450
  "ASCII_2D": 0.125,
1451
  "ASCII_2D_FPV": 0.0,
1452
- "ASCII_3D": 0.0,
1453
- "TOPDOWN_2D": 0.0
1454
  }
1455
  },
1456
  "DNMSTask": {
@@ -1459,208 +1406,195 @@
1459
  "view_mode_scores": {
1460
  "ASCII_2D": 0.44,
1461
  "ASCII_2D_FPV": 0.54,
1462
- "ASCII_3D": 0.29,
1463
- "TOPDOWN_2D": 0.0
1464
  }
1465
  }
1466
  },
1467
- "total_trials": 1352,
1468
  "view_modes": [
1469
  "ASCII_2D",
1470
  "ASCII_2D_FPV",
1471
- "ASCII_3D",
1472
- "TOPDOWN_2D"
1473
  ]
1474
  },
1475
  {
1476
- "model": "InternVL2.5-8B",
1477
- "model_id": "internvl2.5-8b",
1478
- "modality": "text (ASCII)",
1479
  "source": "open-weights/vLLM",
1480
- "overall": 0.4662,
1481
  "overall_by_view": {
1482
- "ASCII_2D": 0.2185222222222222,
1483
- "ASCII_2D_FPV": 0.27342222222222223,
1484
- "ASCII_3D": 0.2538,
1485
- "TOPDOWN_2D": 0.2798111111111111
1486
  },
1487
  "per_environment": {
1488
  "MorrisWaterMaze": {
1489
- "success_rate": 0.6,
1490
- "best_view_mode": "ASCII_3D",
1491
  "view_mode_scores": {
1492
- "ASCII_2D": 0.3,
1493
- "ASCII_2D_FPV": 0.5,
1494
- "ASCII_3D": 0.6,
1495
  "TOPDOWN_2D": 0.55
1496
  }
1497
  },
1498
  "TMaze": {
1499
- "success_rate": 0.4,
1500
- "best_view_mode": "ASCII_2D",
1501
  "view_mode_scores": {
1502
- "ASCII_2D": 0.4,
1503
- "ASCII_2D_FPV": 0.05,
1504
- "ASCII_3D": 0.025,
1505
- "TOPDOWN_2D": 0.35
1506
  }
1507
  },
1508
  "BarnesMaze": {
1509
- "success_rate": 0.5625,
1510
- "best_view_mode": "ASCII_3D",
1511
  "view_mode_scores": {
1512
- "ASCII_2D": 0.0,
1513
- "ASCII_2D_FPV": 0.3125,
1514
- "ASCII_3D": 0.5625,
1515
- "TOPDOWN_2D": 0.0
1516
  }
1517
  },
1518
  "RadialArmMaze": {
1519
- "success_rate": 0.05,
1520
- "best_view_mode": "ASCII_3D",
1521
  "view_mode_scores": {
1522
- "ASCII_2D": 0.0,
1523
- "ASCII_2D_FPV": 0.0,
1524
- "ASCII_3D": 0.05,
1525
  "TOPDOWN_2D": 0.0
1526
  }
1527
  },
1528
  "OperantChamber": {
1529
- "success_rate": 0.22,
1530
- "best_view_mode": "ASCII_3D",
1531
  "view_mode_scores": {
1532
- "ASCII_2D": 0.02,
1533
- "ASCII_2D_FPV": 0.06,
1534
- "ASCII_3D": 0.22,
1535
- "TOPDOWN_2D": 0.0
1536
  }
1537
  },
1538
  "ShuttleBox": {
1539
- "success_rate": 0.95,
1540
  "best_view_mode": "TOPDOWN_2D",
1541
  "view_mode_scores": {
1542
- "ASCII_2D": 0.025,
1543
- "ASCII_2D_FPV": 0.125,
1544
- "ASCII_3D": 0.225,
1545
- "TOPDOWN_2D": 0.95
1546
  }
1547
  },
1548
  "PlacePreference": {
1549
- "success_rate": 0.8333,
1550
- "best_view_mode": "ASCII_2D_FPV",
1551
  "view_mode_scores": {
1552
- "ASCII_2D": 0.6667,
1553
- "ASCII_2D_FPV": 0.8333,
1554
- "ASCII_3D": 0.1667,
1555
- "TOPDOWN_2D": 0.5833
1556
  }
1557
  },
1558
  "StarMaze": {
1559
- "success_rate": 0.1,
1560
- "best_view_mode": "ASCII_2D_FPV",
1561
  "view_mode_scores": {
1562
- "ASCII_2D": 0.075,
1563
- "ASCII_2D_FPV": 0.1,
1564
- "ASCII_3D": 0.025,
1565
  "TOPDOWN_2D": 0.025
1566
  }
1567
  },
1568
  "DNMSTask": {
1569
- "success_rate": 0.48,
1570
- "best_view_mode": "ASCII_2D",
1571
  "view_mode_scores": {
1572
- "ASCII_2D": 0.48,
1573
- "ASCII_2D_FPV": 0.48,
1574
- "ASCII_3D": 0.41,
1575
- "TOPDOWN_2D": 0.06
1576
  }
1577
  }
1578
  },
1579
- "total_trials": 1352,
1580
  "view_modes": [
1581
- "ASCII_2D",
1582
- "ASCII_2D_FPV",
1583
- "ASCII_3D",
1584
  "TOPDOWN_2D"
1585
  ]
1586
  },
1587
  {
1588
- "model": "Qwen2.5-VL-7B",
1589
- "model_id": "qwen2.5vl-7b",
1590
- "modality": "vision",
1591
  "source": "open-weights/vLLM",
1592
- "overall": 0.43027777777777776,
1593
  "overall_by_view": {
1594
- "TOPDOWN_2D": 0.43027777777777776
 
 
1595
  },
1596
  "per_environment": {
1597
  "MorrisWaterMaze": {
1598
- "success_rate": 0.55,
1599
- "best_view_mode": "TOPDOWN_2D",
1600
  "view_mode_scores": {
1601
- "TOPDOWN_2D": 0.55
 
 
1602
  }
1603
  },
1604
  "TMaze": {
1605
- "success_rate": 0.7,
1606
- "best_view_mode": "TOPDOWN_2D",
1607
  "view_mode_scores": {
1608
- "TOPDOWN_2D": 0.7
 
 
1609
  }
1610
  },
1611
  "BarnesMaze": {
1612
- "success_rate": 0.4375,
1613
- "best_view_mode": "TOPDOWN_2D",
1614
  "view_mode_scores": {
1615
- "TOPDOWN_2D": 0.4375
 
 
1616
  }
1617
  },
1618
  "RadialArmMaze": {
1619
- "success_rate": 0.0,
1620
- "best_view_mode": "TOPDOWN_2D",
1621
  "view_mode_scores": {
1622
- "TOPDOWN_2D": 0.0
 
 
1623
  }
1624
  },
1625
  "OperantChamber": {
1626
- "success_rate": 0.66,
1627
- "best_view_mode": "TOPDOWN_2D",
1628
  "view_mode_scores": {
1629
- "TOPDOWN_2D": 0.66
 
 
1630
  }
1631
  },
1632
  "ShuttleBox": {
1633
- "success_rate": 0.6,
1634
- "best_view_mode": "TOPDOWN_2D",
1635
  "view_mode_scores": {
1636
- "TOPDOWN_2D": 0.6
 
 
1637
  }
1638
  },
1639
  "PlacePreference": {
1640
- "success_rate": 0.5,
1641
- "best_view_mode": "TOPDOWN_2D",
1642
  "view_mode_scores": {
1643
- "TOPDOWN_2D": 0.5
 
 
1644
  }
1645
  },
1646
  "StarMaze": {
1647
- "success_rate": 0.025,
1648
- "best_view_mode": "TOPDOWN_2D",
1649
  "view_mode_scores": {
1650
- "TOPDOWN_2D": 0.025
 
 
1651
  }
1652
  },
1653
  "DNMSTask": {
1654
- "success_rate": 0.4,
1655
- "best_view_mode": "TOPDOWN_2D",
1656
  "view_mode_scores": {
1657
- "TOPDOWN_2D": 0.4
 
 
1658
  }
1659
  }
1660
  },
1661
- "total_trials": 338,
1662
  "view_modes": [
1663
- "TOPDOWN_2D"
 
 
1664
  ]
1665
  },
1666
  {
 
741
  "overall_by_view": {
742
  "ASCII_2D": 0.5264777777777777,
743
  "ASCII_2D_FPV": 0.3620333333333334,
744
+ "ASCII_3D": 0.5337999999999998
 
745
  },
746
  "per_environment": {
747
  "MorrisWaterMaze": {
 
750
  "view_mode_scores": {
751
  "ASCII_2D": 0.3,
752
  "ASCII_2D_FPV": 0.95,
753
+ "ASCII_3D": 0.7
 
754
  }
755
  },
756
  "TMaze": {
 
759
  "view_mode_scores": {
760
  "ASCII_2D": 0.7,
761
  "ASCII_2D_FPV": 0.225,
762
+ "ASCII_3D": 0.875
 
763
  }
764
  },
765
  "BarnesMaze": {
 
768
  "view_mode_scores": {
769
  "ASCII_2D": 0.75,
770
  "ASCII_2D_FPV": 0.25,
771
+ "ASCII_3D": 0.4375
 
772
  }
773
  },
774
  "RadialArmMaze": {
 
777
  "view_mode_scores": {
778
  "ASCII_2D": 0.05,
779
  "ASCII_2D_FPV": 0.1,
780
+ "ASCII_3D": 0.05
 
781
  }
782
  },
783
  "OperantChamber": {
 
786
  "view_mode_scores": {
787
  "ASCII_2D": 0.84,
788
  "ASCII_2D_FPV": 0.28,
789
+ "ASCII_3D": 0.84
 
790
  }
791
  },
792
  "ShuttleBox": {
 
795
  "view_mode_scores": {
796
  "ASCII_2D": 0.625,
797
  "ASCII_2D_FPV": 0.8,
798
+ "ASCII_3D": 0.3
 
799
  }
800
  },
801
  "PlacePreference": {
 
804
  "view_mode_scores": {
805
  "ASCII_2D": 0.5833,
806
  "ASCII_2D_FPV": 0.0833,
807
+ "ASCII_3D": 0.9167
 
808
  }
809
  },
810
  "StarMaze": {
 
813
  "view_mode_scores": {
814
  "ASCII_2D": 0.35,
815
  "ASCII_2D_FPV": 0.05,
816
+ "ASCII_3D": 0.175
 
817
  }
818
  },
819
  "DNMSTask": {
 
822
  "view_mode_scores": {
823
  "ASCII_2D": 0.54,
824
  "ASCII_2D_FPV": 0.52,
825
+ "ASCII_3D": 0.51
 
826
  }
827
  }
828
  },
829
+ "total_trials": 1014,
830
  "view_modes": [
831
  "ASCII_2D",
832
  "ASCII_2D_FPV",
833
+ "ASCII_3D"
 
834
  ]
835
  },
836
  {
 
838
  "model_id": "qwen2.5vl-32b",
839
  "modality": "text (ASCII)",
840
  "source": "open-weights/vLLM",
841
+ "overall": 0.6471333333333332,
842
  "overall_by_view": {
843
  "ASCII_2D": 0.4800888888888889,
844
  "ASCII_2D_FPV": 0.5351888888888889,
845
+ "ASCII_3D": 0.43472222222222223
 
846
  },
847
  "per_environment": {
848
  "MorrisWaterMaze": {
 
851
  "view_mode_scores": {
852
  "ASCII_2D": 0.95,
853
  "ASCII_2D_FPV": 0.45,
854
+ "ASCII_3D": 0.45
 
855
  }
856
  },
857
  "TMaze": {
 
860
  "view_mode_scores": {
861
  "ASCII_2D": 0.125,
862
  "ASCII_2D_FPV": 0.825,
863
+ "ASCII_3D": 0.275
 
864
  }
865
  },
866
  "BarnesMaze": {
 
869
  "view_mode_scores": {
870
  "ASCII_2D": 0.6875,
871
  "ASCII_2D_FPV": 0.5,
872
+ "ASCII_3D": 0.4375
 
873
  }
874
  },
875
  "RadialArmMaze": {
 
878
  "view_mode_scores": {
879
  "ASCII_2D": 0.0,
880
  "ASCII_2D_FPV": 0.0,
881
+ "ASCII_3D": 0.0
 
882
  }
883
  },
884
  "OperantChamber": {
 
887
  "view_mode_scores": {
888
  "ASCII_2D": 0.28,
889
  "ASCII_2D_FPV": 1.0,
890
+ "ASCII_3D": 0.76
 
891
  }
892
  },
893
  "ShuttleBox": {
 
896
  "view_mode_scores": {
897
  "ASCII_2D": 0.95,
898
  "ASCII_2D_FPV": 0.825,
899
+ "ASCII_3D": 0.85
 
900
  }
901
  },
902
  "PlacePreference": {
903
+ "success_rate": 0.6667,
904
+ "best_view_mode": "ASCII_2D_FPV",
905
  "view_mode_scores": {
906
  "ASCII_2D": 0.5833,
907
  "ASCII_2D_FPV": 0.6667,
908
+ "ASCII_3D": 0.5
 
909
  }
910
  },
911
  "StarMaze": {
 
914
  "view_mode_scores": {
915
  "ASCII_2D": 0.225,
916
  "ASCII_2D_FPV": 0.15,
917
+ "ASCII_3D": 0.2
 
918
  }
919
  },
920
  "DNMSTask": {
 
923
  "view_mode_scores": {
924
  "ASCII_2D": 0.52,
925
  "ASCII_2D_FPV": 0.4,
926
+ "ASCII_3D": 0.44
 
927
  }
928
  }
929
  },
930
+ "total_trials": 1014,
931
  "view_modes": [
932
  "ASCII_2D",
933
  "ASCII_2D_FPV",
934
+ "ASCII_3D"
 
935
  ]
936
  },
937
  {
 
939
  "model_id": "qwen2.5vl-72b",
940
  "modality": "text (ASCII)",
941
  "source": "open-weights/vLLM",
942
+ "overall": 0.5849111111111109,
943
  "overall_by_view": {
944
  "ASCII_2D": 0.49342222222222226,
945
  "ASCII_2D_FPV": 0.49518888888888885,
946
+ "ASCII_3D": 0.47213333333333324
 
947
  },
948
  "per_environment": {
949
  "MorrisWaterMaze": {
 
952
  "view_mode_scores": {
953
  "ASCII_2D": 0.8,
954
  "ASCII_2D_FPV": 0.6,
955
+ "ASCII_3D": 0.85
 
956
  }
957
  },
958
  "TMaze": {
 
961
  "view_mode_scores": {
962
  "ASCII_2D": 0.625,
963
  "ASCII_2D_FPV": 0.725,
964
+ "ASCII_3D": 0.425
 
965
  }
966
  },
967
  "BarnesMaze": {
968
+ "success_rate": 0.4375,
969
+ "best_view_mode": "ASCII_2D",
970
  "view_mode_scores": {
971
  "ASCII_2D": 0.4375,
972
  "ASCII_2D_FPV": 0.375,
973
+ "ASCII_3D": 0.0625
 
974
  }
975
  },
976
  "RadialArmMaze": {
 
979
  "view_mode_scores": {
980
  "ASCII_2D": 0.0,
981
  "ASCII_2D_FPV": 0.0,
982
+ "ASCII_3D": 0.0
 
983
  }
984
  },
985
  "OperantChamber": {
 
988
  "view_mode_scores": {
989
  "ASCII_2D": 0.94,
990
  "ASCII_2D_FPV": 0.98,
991
+ "ASCII_3D": 0.92
 
992
  }
993
  },
994
  "ShuttleBox": {
995
+ "success_rate": 0.7,
996
+ "best_view_mode": "ASCII_3D",
997
  "view_mode_scores": {
998
  "ASCII_2D": 0.35,
999
  "ASCII_2D_FPV": 0.6,
1000
+ "ASCII_3D": 0.7
 
1001
  }
1002
  },
1003
  "PlacePreference": {
 
1006
  "view_mode_scores": {
1007
  "ASCII_2D": 0.5833,
1008
  "ASCII_2D_FPV": 0.6667,
1009
+ "ASCII_3D": 0.4167
 
1010
  }
1011
  },
1012
  "StarMaze": {
 
1015
  "view_mode_scores": {
1016
  "ASCII_2D": 0.225,
1017
  "ASCII_2D_FPV": 0.05,
1018
+ "ASCII_3D": 0.425
 
1019
  }
1020
  },
1021
  "DNMSTask": {
 
1024
  "view_mode_scores": {
1025
  "ASCII_2D": 0.48,
1026
  "ASCII_2D_FPV": 0.46,
1027
+ "ASCII_3D": 0.45
 
1028
  }
1029
  }
1030
  },
1031
+ "total_trials": 1014,
1032
  "view_modes": [
1033
  "ASCII_2D",
1034
  "ASCII_2D_FPV",
1035
+ "ASCII_3D"
 
1036
  ]
1037
  },
1038
  {
 
1141
  "model_id": "qwen2.5vl-3b",
1142
  "modality": "text (ASCII)",
1143
  "source": "open-weights/vLLM",
1144
+ "overall": 0.5151888888888888,
1145
  "overall_by_view": {
1146
  "ASCII_2D": 0.25869999999999993,
1147
  "ASCII_2D_FPV": 0.22425555555555554,
1148
+ "ASCII_3D": 0.4126888888888889
 
1149
  },
1150
  "per_environment": {
1151
  "MorrisWaterMaze": {
 
1154
  "view_mode_scores": {
1155
  "ASCII_2D": 0.45,
1156
  "ASCII_2D_FPV": 0.55,
1157
+ "ASCII_3D": 0.95
 
1158
  }
1159
  },
1160
  "TMaze": {
 
1163
  "view_mode_scores": {
1164
  "ASCII_2D": 0.125,
1165
  "ASCII_2D_FPV": 0.1,
1166
+ "ASCII_3D": 1.0
 
1167
  }
1168
  },
1169
  "BarnesMaze": {
 
1172
  "view_mode_scores": {
1173
  "ASCII_2D": 0.375,
1174
  "ASCII_2D_FPV": 0.125,
1175
+ "ASCII_3D": 0.0625
 
1176
  }
1177
  },
1178
  "RadialArmMaze": {
 
1181
  "view_mode_scores": {
1182
  "ASCII_2D": 0.0,
1183
  "ASCII_2D_FPV": 0.0,
1184
+ "ASCII_3D": 0.0
 
1185
  }
1186
  },
1187
  "OperantChamber": {
 
1190
  "view_mode_scores": {
1191
  "ASCII_2D": 0.14,
1192
  "ASCII_2D_FPV": 0.54,
1193
+ "ASCII_3D": 0.04
 
1194
  }
1195
  },
1196
  "ShuttleBox": {
 
1199
  "view_mode_scores": {
1200
  "ASCII_2D": 0.525,
1201
  "ASCII_2D_FPV": 0.225,
1202
+ "ASCII_3D": 0.675
 
1203
  }
1204
  },
1205
  "PlacePreference": {
 
1208
  "view_mode_scores": {
1209
  "ASCII_2D": 0.3333,
1210
  "ASCII_2D_FPV": 0.3333,
1211
+ "ASCII_3D": 0.6667
 
1212
  }
1213
  },
1214
  "StarMaze": {
 
1217
  "view_mode_scores": {
1218
  "ASCII_2D": 0.0,
1219
  "ASCII_2D_FPV": 0.025,
1220
+ "ASCII_3D": 0.05
 
1221
  }
1222
  },
1223
  "DNMSTask": {
1224
+ "success_rate": 0.38,
1225
+ "best_view_mode": "ASCII_2D",
1226
  "view_mode_scores": {
1227
  "ASCII_2D": 0.38,
1228
  "ASCII_2D_FPV": 0.12,
1229
+ "ASCII_3D": 0.27
 
1230
  }
1231
  }
1232
  },
1233
+ "total_trials": 1014,
1234
  "view_modes": [
1235
  "ASCII_2D",
1236
  "ASCII_2D_FPV",
1237
+ "ASCII_3D"
 
1238
  ]
1239
  },
1240
  {
 
1321
  "model_id": "phi-4-mm-14b",
1322
  "modality": "text (ASCII)",
1323
  "source": "open-weights/vLLM",
1324
+ "overall": 0.4748111111111111,
1325
  "overall_by_view": {
1326
  "ASCII_2D": 0.37147777777777774,
1327
  "ASCII_2D_FPV": 0.32147777777777775,
1328
+ "ASCII_3D": 0.24286666666666668
 
1329
  },
1330
  "per_environment": {
1331
  "MorrisWaterMaze": {
 
1334
  "view_mode_scores": {
1335
  "ASCII_2D": 0.85,
1336
  "ASCII_2D_FPV": 0.1,
1337
+ "ASCII_3D": 0.15
 
1338
  }
1339
  },
1340
  "TMaze": {
 
1343
  "view_mode_scores": {
1344
  "ASCII_2D": 0.575,
1345
  "ASCII_2D_FPV": 0.5,
1346
+ "ASCII_3D": 0.325
 
1347
  }
1348
  },
1349
  "BarnesMaze": {
1350
+ "success_rate": 0.25,
1351
+ "best_view_mode": "ASCII_2D",
1352
  "view_mode_scores": {
1353
  "ASCII_2D": 0.25,
1354
  "ASCII_2D_FPV": 0.125,
1355
+ "ASCII_3D": 0.1875
 
1356
  }
1357
  },
1358
  "RadialArmMaze": {
 
1361
  "view_mode_scores": {
1362
  "ASCII_2D": 0.0,
1363
  "ASCII_2D_FPV": 0.0,
1364
+ "ASCII_3D": 0.0
 
1365
  }
1366
  },
1367
  "OperantChamber": {
 
1370
  "view_mode_scores": {
1371
  "ASCII_2D": 0.52,
1372
  "ASCII_2D_FPV": 0.42,
1373
+ "ASCII_3D": 0.6
 
1374
  }
1375
  },
1376
  "ShuttleBox": {
 
1379
  "view_mode_scores": {
1380
  "ASCII_2D": 0.5,
1381
  "ASCII_2D_FPV": 0.375,
1382
+ "ASCII_3D": 0.3
 
1383
  }
1384
  },
1385
  "PlacePreference": {
 
1388
  "view_mode_scores": {
1389
  "ASCII_2D": 0.0833,
1390
  "ASCII_2D_FPV": 0.8333,
1391
+ "ASCII_3D": 0.3333
 
1392
  }
1393
  },
1394
  "StarMaze": {
 
1397
  "view_mode_scores": {
1398
  "ASCII_2D": 0.125,
1399
  "ASCII_2D_FPV": 0.0,
1400
+ "ASCII_3D": 0.0
 
1401
  }
1402
  },
1403
  "DNMSTask": {
 
1406
  "view_mode_scores": {
1407
  "ASCII_2D": 0.44,
1408
  "ASCII_2D_FPV": 0.54,
1409
+ "ASCII_3D": 0.29
 
1410
  }
1411
  }
1412
  },
1413
+ "total_trials": 1014,
1414
  "view_modes": [
1415
  "ASCII_2D",
1416
  "ASCII_2D_FPV",
1417
+ "ASCII_3D"
 
1418
  ]
1419
  },
1420
  {
1421
+ "model": "Qwen2.5-VL-7B",
1422
+ "model_id": "qwen2.5vl-7b",
1423
+ "modality": "vision",
1424
  "source": "open-weights/vLLM",
1425
+ "overall": 0.43027777777777776,
1426
  "overall_by_view": {
1427
+ "TOPDOWN_2D": 0.43027777777777776
 
 
 
1428
  },
1429
  "per_environment": {
1430
  "MorrisWaterMaze": {
1431
+ "success_rate": 0.55,
1432
+ "best_view_mode": "TOPDOWN_2D",
1433
  "view_mode_scores": {
 
 
 
1434
  "TOPDOWN_2D": 0.55
1435
  }
1436
  },
1437
  "TMaze": {
1438
+ "success_rate": 0.7,
1439
+ "best_view_mode": "TOPDOWN_2D",
1440
  "view_mode_scores": {
1441
+ "TOPDOWN_2D": 0.7
 
 
 
1442
  }
1443
  },
1444
  "BarnesMaze": {
1445
+ "success_rate": 0.4375,
1446
+ "best_view_mode": "TOPDOWN_2D",
1447
  "view_mode_scores": {
1448
+ "TOPDOWN_2D": 0.4375
 
 
 
1449
  }
1450
  },
1451
  "RadialArmMaze": {
1452
+ "success_rate": 0.0,
1453
+ "best_view_mode": "TOPDOWN_2D",
1454
  "view_mode_scores": {
 
 
 
1455
  "TOPDOWN_2D": 0.0
1456
  }
1457
  },
1458
  "OperantChamber": {
1459
+ "success_rate": 0.66,
1460
+ "best_view_mode": "TOPDOWN_2D",
1461
  "view_mode_scores": {
1462
+ "TOPDOWN_2D": 0.66
 
 
 
1463
  }
1464
  },
1465
  "ShuttleBox": {
1466
+ "success_rate": 0.6,
1467
  "best_view_mode": "TOPDOWN_2D",
1468
  "view_mode_scores": {
1469
+ "TOPDOWN_2D": 0.6
 
 
 
1470
  }
1471
  },
1472
  "PlacePreference": {
1473
+ "success_rate": 0.5,
1474
+ "best_view_mode": "TOPDOWN_2D",
1475
  "view_mode_scores": {
1476
+ "TOPDOWN_2D": 0.5
 
 
 
1477
  }
1478
  },
1479
  "StarMaze": {
1480
+ "success_rate": 0.025,
1481
+ "best_view_mode": "TOPDOWN_2D",
1482
  "view_mode_scores": {
 
 
 
1483
  "TOPDOWN_2D": 0.025
1484
  }
1485
  },
1486
  "DNMSTask": {
1487
+ "success_rate": 0.4,
1488
+ "best_view_mode": "TOPDOWN_2D",
1489
  "view_mode_scores": {
1490
+ "TOPDOWN_2D": 0.4
 
 
 
1491
  }
1492
  }
1493
  },
1494
+ "total_trials": 338,
1495
  "view_modes": [
 
 
 
1496
  "TOPDOWN_2D"
1497
  ]
1498
  },
1499
  {
1500
+ "model": "InternVL2.5-8B",
1501
+ "model_id": "internvl2.5-8b",
1502
+ "modality": "text (ASCII)",
1503
  "source": "open-weights/vLLM",
1504
+ "overall": 0.38564444444444446,
1505
  "overall_by_view": {
1506
+ "ASCII_2D": 0.2185222222222222,
1507
+ "ASCII_2D_FPV": 0.27342222222222223,
1508
+ "ASCII_3D": 0.2538
1509
  },
1510
  "per_environment": {
1511
  "MorrisWaterMaze": {
1512
+ "success_rate": 0.6,
1513
+ "best_view_mode": "ASCII_3D",
1514
  "view_mode_scores": {
1515
+ "ASCII_2D": 0.3,
1516
+ "ASCII_2D_FPV": 0.5,
1517
+ "ASCII_3D": 0.6
1518
  }
1519
  },
1520
  "TMaze": {
1521
+ "success_rate": 0.4,
1522
+ "best_view_mode": "ASCII_2D",
1523
  "view_mode_scores": {
1524
+ "ASCII_2D": 0.4,
1525
+ "ASCII_2D_FPV": 0.05,
1526
+ "ASCII_3D": 0.025
1527
  }
1528
  },
1529
  "BarnesMaze": {
1530
+ "success_rate": 0.5625,
1531
+ "best_view_mode": "ASCII_3D",
1532
  "view_mode_scores": {
1533
+ "ASCII_2D": 0.0,
1534
+ "ASCII_2D_FPV": 0.3125,
1535
+ "ASCII_3D": 0.5625
1536
  }
1537
  },
1538
  "RadialArmMaze": {
1539
+ "success_rate": 0.05,
1540
+ "best_view_mode": "ASCII_3D",
1541
  "view_mode_scores": {
1542
+ "ASCII_2D": 0.0,
1543
+ "ASCII_2D_FPV": 0.0,
1544
+ "ASCII_3D": 0.05
1545
  }
1546
  },
1547
  "OperantChamber": {
1548
+ "success_rate": 0.22,
1549
+ "best_view_mode": "ASCII_3D",
1550
  "view_mode_scores": {
1551
+ "ASCII_2D": 0.02,
1552
+ "ASCII_2D_FPV": 0.06,
1553
+ "ASCII_3D": 0.22
1554
  }
1555
  },
1556
  "ShuttleBox": {
1557
+ "success_rate": 0.225,
1558
+ "best_view_mode": "ASCII_3D",
1559
  "view_mode_scores": {
1560
+ "ASCII_2D": 0.025,
1561
+ "ASCII_2D_FPV": 0.125,
1562
+ "ASCII_3D": 0.225
1563
  }
1564
  },
1565
  "PlacePreference": {
1566
+ "success_rate": 0.8333,
1567
+ "best_view_mode": "ASCII_2D_FPV",
1568
  "view_mode_scores": {
1569
+ "ASCII_2D": 0.6667,
1570
+ "ASCII_2D_FPV": 0.8333,
1571
+ "ASCII_3D": 0.1667
1572
  }
1573
  },
1574
  "StarMaze": {
1575
+ "success_rate": 0.1,
1576
+ "best_view_mode": "ASCII_2D_FPV",
1577
  "view_mode_scores": {
1578
+ "ASCII_2D": 0.075,
1579
+ "ASCII_2D_FPV": 0.1,
1580
+ "ASCII_3D": 0.025
1581
  }
1582
  },
1583
  "DNMSTask": {
1584
+ "success_rate": 0.48,
1585
+ "best_view_mode": "ASCII_2D",
1586
  "view_mode_scores": {
1587
+ "ASCII_2D": 0.48,
1588
+ "ASCII_2D_FPV": 0.48,
1589
+ "ASCII_3D": 0.41
1590
  }
1591
  }
1592
  },
1593
+ "total_trials": 1014,
1594
  "view_modes": [
1595
+ "ASCII_2D",
1596
+ "ASCII_2D_FPV",
1597
+ "ASCII_3D"
1598
  ]
1599
  },
1600
  {