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

Multiple Choice Question Answering on MMLU STEM

84.91Score

Qwen2.5(14B)T

50.860459.700268.5477.3798Jul 4, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
84.91--
2026.07
75.55--
2026.07
59.462.752
2026.07
56.7102.4
2026.07
56.3-0.413
2026.07
53.850.282
2026.07
53.5702.4
2026.07
53.44-0.132.6
2026.07
52.55-4.162.6
2026.07
52.17-1.43