Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

General VQA on HRBench

78.5Accuracy

GPT 5 + Tools

51.064858.187465.3172.4326Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
78.5
2026.01
78.25
2026.01
75.12
2026.01
74.38
2026.01
73
2026.01
70.12
2026.01
69.12
2026.01
67.12
2026.01
67
2026.01
63.75
2026.01
63.62
2026.01
60.62
2026.01
53
2026.01
52.12