Multimodal Tool-use Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.23Accuracy
23
May 12, 2026
83.21Accuracy
7
Feb 26, 2026
93.55Alg. Accuracy
7
Feb 26, 2026
46Cultural Understanding Score
7
Feb 26, 2026
88Accuracy (Biology)
7
Feb 26, 2026