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

Mathematical Reasoning on OlympiadBench (Accuracy, Pass@1)

64Pass@1

Qwen3-4B-Instruct-2507

37.79244.59651.458.204Dec 8, 2025Dec 17, 2025Dec 26, 2025Jan 4, 2026Jan 13, 2026Jan 22, 2026Jan 31, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.12
64-
2025.12
63.7-
2025.12
62.2-
2025.12
61.9-
2025.12
60.1-
2025.12
57.8-
2025.12
56.3-
2025.12
48.6-
2025.12
48-
2025.12
46.4-
2026.01
41.9-
2025.12
38.8-