Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Reasoning on MATH (Accuracy, Latency, Speedup)

92.84Accuracy (%)

LR

48.348859.899471.4583.0006Mar 13, 2026Mar 22, 2026Mar 31, 2026Apr 10, 2026Apr 19, 2026Apr 28, 2026May 8, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.03
92.849.561.2
2026.03
91.5411
2026.03
91.3710.631.24
2026.03
89.876.211.1
2026.03
60.6613.54
2026.05
52.88--
2026.05
50.06--