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

Multiple-choice Reasoning on MMLU

32.8Accuracy

FineWeb-Edu

29.78430.56731.3532.133Apr 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
32.8
2026.04
32.2
2026.04
31.5
2026.04
31.5
2026.04
31.4
2026.04
31.2
2026.04
31.1
2026.04
30.6
2026.04
30.2
2026.04
29.9