Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
61Pass@1 Accuracy
3
Feb 26, 2026
65Pass@1 Accuracy
3
Feb 26, 2026
86Pass@1 Accuracy
3
Feb 26, 2026
92Pass@1 Accuracy
3
Feb 26, 2026
58.6F-P Score
3
Feb 26, 2026
54Accuracy
3
Feb 26, 2026
62.8Accuracy
3
Feb 26, 2026
63.43Average Accuracy
2
Jun 23, 2026
81.83Accuracy
2
Jun 23, 2026
56.28Accuracy
2
Jun 23, 2026
70.72Accuracy
2
Jun 23, 2026
54Accuracy
2
Jun 23, 2026
18.55BLEU-1
2
Mar 10, 2026