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

Vision-centric Evaluation on CV-Bench

0.8751Accuracy

Qwen3-VL-32B

0.3448040.4824770.620150.757823Jan 12, 2026Feb 7, 2026Mar 5, 2026Mar 31, 2026Apr 26, 2026May 22, 2026Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.8751
2026.01
0.864
2026.06
0.8596
2026.06
0.8563
2026.01
0.855
2026.06
0.8546
2026.01
0.849
2026.01
0.844
2026.06
0.8199
2026.01
0.818
2026.06
0.8086
2026.01
0.807
2026.06
0.8064
2026.06
0.7909
2026.06
0.7737
2026.06
0.7603
2026.01
0.76
2026.06
0.7561
2026.01
0.754
2026.01
0.748
2026.01
0.737
2026.01
0.714
2026.06
0.6783
2026.01
0.619
2026.01
0.613
2026.01
0.588
2026.01
0.588
2026.01
0.535
2026.01
0.474
2026.01
0.461
0.46
2026.01
0.421
2026.01
0.379
2026.06
0.3652