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

Robust Reasoning on MMLU-Pro (Accuracy)

21Accuracy

NITP

6.585610.327814.0717.8122May 24, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
21
2026.05
15.29
2026.05
12.29
2026.05
11
2026.05
7.47
2026.05
7.14