Multimodal Scientific Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.07Accuracy
28
Apr 23, 2026
56.66Accuracy (%)
16
Jun 16, 2026
68.1Accuracy
16
Jun 16, 2026
49.3Accuracy
16
Jun 16, 2026
71.77Accuracy
8
Apr 7, 2026
68.25Accuracy
8
Apr 7, 2026
28.95Accuracy
8
Apr 7, 2026