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

General Knowledge Reasoning on MMLU-Pro (Acc, Ent)

75.41Accuracy (MMLU-Pro)

Policy Split

53.5759.2464.9170.58Apr 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
75.410.85
2026.04
75.360.54
2026.04
75.160.54
2026.04
75.050.54
2026.04
74.840.72
2026.04
74.420.66
2026.04
74.380.56
2026.04
73.860.54
2026.04
73.041.02
2026.04
69.070.55
2026.04
68.80.55
2026.04
68.680.73
2026.04
68.30.55
2026.04
68.30.76
2026.04
68.020.55
2026.04
67.680.84
2026.04
67.630.65
2026.04
66.790.55
2026.04
56.660.45
2026.04
56.620.92
2026.04
56.520.48
2026.04
56.460.96
2026.04
56.070.74
2026.04
560.46
2026.04
55.910.46
2026.04
55.710.46
2026.04
54.411.03