Text-Vision Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62Pass@1 Acc
5
Feb 26, 2026
54Pass@1 Accuracy
5
Feb 26, 2026
57Pass@1 Accuracy
5
Feb 26, 2026
59Pass@1 Accuracy
5
Feb 26, 2026
0.65Pass@1 Accuracy
5
Feb 26, 2026
88Pass@1 Accuracy
5
Feb 26, 2026