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

Multi-task Language Understanding on MMLU Pro (Subject Breakdown)

76.88MMLU Pro Engineering Acc

Qwen3-Next-80B-A3B-Thinking

13.564830.002446.4462.8776Nov 25, 2025Nov 28, 2025Dec 2, 2025Dec 6, 2025Dec 10, 2025Dec 14, 2025Dec 18, 2025
Updated 15d ago

Evaluation Results

MethodLinks
2025.12
76.8875.0672.95-
2025.12
74.9275.9273.35-
2025.12
74.7276.7772.14-
2025.12
73.3776.1671.34-
2025.12
72.5574.8269.34-
2025.12
71.5274.9469.74-
2025.12
71.4175.6772.55-
2025.12
70.7976.2872.14-
2025.12
67.775.3169.54-
2025.11
67-8085
2025.12
66.7767.1155.31-
2025.12
66.1567.4857.11-
2025.11
65-7784
2025.11
65-8086
2025.11
64-7885
2025.11
64-7684
2025.11
63-7884
2025.11
63-7684
2025.11
63-7983
2025.11
63-7886
2025.11
62-7784
2025.12
61.6167.2458.72-
2025.12
61.266.1459.32-
2025.11
56-6677
2025.11
56-7280
2025.11
52-6579
2025.11
52-6079
2025.11
46-7583
2025.11
46-7582
2025.11
46-7483
2025.11
46-7985
2025.11
45-7583
2025.11
44-6979
2025.11
43-7279
2025.11
43-7883
2025.11
42-7884
2025.11
42-7283
2025.11
42-6980
2025.11
39-7179
2025.11
39-7583
2025.11
16-5464