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

Math on APT-Bench

70.5Accuracy

Qwen3

59.37262.26165.1568.039Dec 31, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
70.5
2025.12
68
2025.12
60.7
2025.12
60.1
2025.12
59.9
2025.12
59.8