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

Mathematical Problem Solving on OlympiadBench

53.66Best-of-N Accuracy

MSV 64

40.545643.950347.35550.7597Mar 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
53.66
2026.03
52.23
2026.03
52.1
2026.03
51.54
2026.03
51.12
2026.03
51.04
2026.03
50.87
2026.03
50.39
2026.03
48.95
2026.03
47.7
2026.03
47.55
2026.03
47.47
2026.03
47.25
2026.03
46.81
2026.03
46.29
2026.03
41.05
2026.03
41.05