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

Reasoning on MMLU Redux

67.3Accuracy

Qwen3-1.7B-ALLMEM

44.00450.05256.162.148Feb 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
67.3
2026.02
66.5
2026.02
47.05
2026.02
44.9