Visual Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
34.6Accuracy
8
Mar 4, 2026
73.1Accuracy
8
Mar 4, 2026
54.56BLEU-4
8
Feb 26, 2026
41.1Accuracy
8
Feb 26, 2026
44.7Accuracy
8
Feb 26, 2026
62.9Accuracy
8
Feb 26, 2026
64.3ACC
8
Feb 26, 2026
30.46LLM-J Score (Qwen2.5-7B)
8
Feb 26, 2026
59.5LLM-J Score (Qwen2.5-7B)
8
Feb 26, 2026
60.1PubMed Score
8
Feb 26, 2026
92.4Accuracy (Yes/No)
8
Feb 26, 2026
83.56Gen. Acc
8
Feb 26, 2026
83.2Score
8
Feb 26, 2026
85.86Accuracy
8
Feb 26, 2026
88.26Accuracy
8
Feb 26, 2026
89.86Accuracy
8
Feb 26, 2026
77.45SLAKE
8
Feb 26, 2026
73.8Accuracy
8
Feb 26, 2026
69.4VQAv2 Acc
8
Feb 26, 2026
93.16Accuracy
8
Feb 26, 2026
85.99Accuracy
8
Feb 26, 2026
0.94Descriptive Accuracy
8
Feb 26, 2026
40.07Accuracy
8
Feb 26, 2026
39.8Accuracy
7
Jul 9, 2026
67.2Accuracy
7
Jul 9, 2026