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

Scientific Reasoning on ChemBench (test)

66Initial Score

QWEN3-MAX

49.8854.06558.2562.435May 11, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
6611.50.567
2026.05
63-2.502.560.5
2026.05
61.503.53.561.5
2026.05
61.5812.54.569.5
2026.05
60.524262.5
2026.05
59.50.532.560
2026.05
59.514360.5
2026.05
56-1.512.554.5
2026.05
55.5-0.51.5255
2026.05
550.52.5255.5
2026.05
53.5-0.511.553
2026.05
52.51.542.554
2026.05
50.510.516.5661