Visual Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.33MMMU Score
3
Mar 4, 2026
77.3Accuracy
3
Feb 27, 2026
0.095BLEU-4
3
Feb 26, 2026
0.375BLEU-4
3
Feb 26, 2026
64.92RAD (Y/N | C)
3
Feb 26, 2026
72.87Y/N Accuracy (C)
3
Feb 26, 2026
69.8VQA Accuracy
3
Feb 26, 2026
0.482METEOR
3
Feb 26, 2026
74VQA Acc.
3
Feb 26, 2026
76.77Pass@1
3
Feb 26, 2026
43Volume Score
3
Feb 26, 2026
64.93Accuracy (Mix)
3
Feb 26, 2026
29.03Acc (Open)
3
Feb 26, 2026
26.2Avg Accuracy (1-2)
3
Feb 26, 2026
30Avg Accuracy (1-2 ICL)
3
Feb 26, 2026
82Accuracy
3
Feb 27, 2026
84Accuracy
3
Feb 27, 2026
0.71CIDEr
3
Feb 26, 2026
60.85Accuracy
3
Feb 27, 2026
37.77Percentage Woman
3
Feb 26, 2026
10.61AUC
3
Feb 26, 2026
25.53AUC
3
Feb 26, 2026
86Exact Match
3
Feb 26, 2026
94.84Accuracy
3
Feb 26, 2026
60.15Accuracy
3
Feb 26, 2026