Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
59.49Accuracy
10
Jun 19, 2026
69.5Accuracy
10
Jun 2, 2026
72.4Accuracy
10
Jun 2, 2026
0.832Accuracy
10
Jun 2, 2026
63.16Average Score
10
Apr 15, 2026
59.82AVG Score
10
Apr 15, 2026
65.83Average Performance
10
Apr 15, 2026
80.61Avg@8 Accuracy
10
Apr 15, 2026
67.4Accuracy
10
Apr 14, 2026
71.8MM-Vet v2 Score
10
Mar 4, 2026
27.3Accuracy
10
Feb 26, 2026
31Chemistry Score
10
Feb 26, 2026
61.35Final Score
10
Feb 26, 2026
62.33MiniGPT-4 Score
10
Feb 26, 2026
84.58Accuracy
9
Jun 2, 2026
4,329.3Length (tokens)
9
Jun 1, 2026
3,296.8Token Length
9
Jun 1, 2026
481.8Generated Token Length
9
Jun 1, 2026
2,577.2Generated Token Length (tokens)
9
Jun 1, 2026
5,511.1Token Count
9
Jun 1, 2026
6,448Generated Token Length
9
Jun 1, 2026
54.9Causal Score
9
May 19, 2026
310.36IE-reasoning Score
9
Mar 17, 2026
28.2Accuracy
8
Jul 3, 2026
28.4Accuracy
8
Jun 23, 2026