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

Math Reasoning on OlympiadBench (Pass@1 accuracy)

48.2Pass@1 Accuracy

s1.1-7B

22.228.9535.742.45Dec 16, 2025Dec 20, 2025Dec 25, 2025Dec 30, 2025Jan 3, 2026Jan 8, 2026Jan 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
48.2
2026.01
41.7
2026.01
40.6
2025.12
38.7
2026.01
38
2025.12
37.9
2026.01
35.6
2025.12
34.3
2025.12
33.7
2025.12
32.7
2025.12
32
2026.01
31.3
2026.01
31.2
2026.01
30.6
2026.01
30.5
2025.12
30.2
2025.12
27.6
2025.12
23.8
2025.12
23.2