Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLM Routing on MMLU-PRO, SUPERGPQA, MEDMCQA, and BBEH (test)

91.5MMLU-PRO Top-1 Acc

ORACLE

51.35661.77872.282.622Jan 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
91.5-77.6-96.3-66.4-83-
2026.01
84.4-67.8-91.2-56.7-75-
2026.01
79.480.954.454.792.788.53434.365.164.6
2026.01
74.878.243.648.176.179.631.631.656.559.4
2026.01
74.678.742.649.281.684.132.132.357.761.1
2026.01
73.8-40.8-79.2-34.5-57.1-
2026.01
71.977.539.244.580.784.134.332.656.559.7
2026.01
71.9-49.4-86.6-27.5-58.9-
2026.01
66.265.737.335.77170.225.12549.949.2
2026.01
57.161.732.131.260.865.320.622.842.745.3
2026.01
54.7-25.9-59.8-22.4-40.7-
2026.01
54.357.825.727.659.765.321.722.740.443.4
2026.01
53.9-28.8-57-24.4-41-
2026.01
52.958.925.630.856.865.321.423.439.244.6