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

Multi-discipline Knowledge Evaluation on CodaSet ID MMLU-PRO (test)

84.86Accuracy

Qwen3-235B-A22B

64.78869.99975.2180.421May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
84.865.8
83.945.2
83.764
2026.05
81.826
81.7511.6
2026.05
80.362.2
80.212.8
2026.05
79.994.4
2026.05
79.772
2026.05
79.744.3
77.924.8
2026.05
77.512.5
73.771.9
71.583.5
69.641
2026.05
65.561.1