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

Question Answering on MMLU (Accuracy, Avg, ΔScore)

77.84Accuracy

Qwen3-30BA3B

-2.55896818.31384139.1866560.059459Oct 8, 2025Nov 3, 2025Nov 29, 2025Dec 25, 2025Jan 20, 2026Feb 15, 2026Mar 13, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.10
77.84--
2025.10
75.51--
2026.03
0.72220.79120
2026.03
0.720.7702-2.1
2026.03
0.71780.7567-3.45
2026.03
0.66440.70470
2026.03
0.54670.681-2.37
2026.03
0.53330.6272-7.75