Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
53Accuracy
16
Jul 3, 2026
56.08Accuracy
16
Jun 15, 2026
55.44Accuracy
16
Jun 15, 2026
87Accuracy
16
May 27, 2026
57.6Accuracy
16
May 27, 2026
82.1Accuracy
16
May 27, 2026
67.1Pass@1 Accuracy
16
Apr 14, 2026
41.5Score
16
Apr 23, 2026
76.2Pass@1 Accuracy
16
Apr 14, 2026
90.1Accuracy
15
Mar 27, 2026
82.8Accuracy
15
Mar 17, 2026
90.57CP
15
Feb 26, 2026
71.9Accuracy
14
Jun 25, 2026
93.7Accuracy
14
May 26, 2026
55Accuracy
14
Apr 7, 2026
82.8Accuracy
14
Feb 26, 2026
89Creation Score
14
Feb 26, 2026
49.7Accuracy
13
Jun 2, 2026
74.6BLEU
13
May 12, 2026
79.86Score
13
May 12, 2026
2,393Sum Score
13
Apr 21, 2026
32.4Overall Score
13
Feb 26, 2026
11Pass@1
13
Mar 24, 2026
63.51Score
13
Feb 26, 2026
82.45NS Score
12
Jun 26, 2026