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

Reasoning on AIME24, AIME25, HMMT25 Average

68.6Accuracy

SC@64

18.78431.71744.6557.583Feb 3, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
68.631.91,100.7
2026.02
68.6399.1399.1
2026.02
68.6133.9771.5
2026.02
68.521.6824.9
2026.02
66.831.21,047.7
2026.02
66.8136.6770.8
2026.02
66.820.9789
2026.02
66.7342.2342.2
2026.02
65.126.6880.2
2026.02
63.227.4889.5
2026.02
4731.31,070.9
2026.02
47556.6556.6
2026.02
47168.6945.7
2026.02
45.121.5794.8
2026.02
4226.9888.8
2026.02
23.320.3735.3
2026.02
22.831.6945.7
2026.02
22.8680680
2026.02
22.8181.4926.5
2026.02
20.726.8816.1