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

Reasoning on 7 reasoning datasets

65.74Reasoning Accuracy

PASER

53.811256.908160.00563.1019Feb 18, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.02
65.74
2025.02
63.79
2025.02
62.91
2025.02
62.68
2025.02
60.99
2025.02
60.96
2025.02
60.93
2025.02
60.76
2025.02
60.65
2025.02
58.94
2025.02
58.31
2025.02
57.78
2025.02
57.53
2025.02
56.68
2025.02
54.27