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

Mathematical Reasoning on AMC 23 (Pass@1, TPS, Latency)

92.5Pass@1

Target Model

60.15668.55376.9585.347Feb 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
92.534.78154.34
2026.02
92.540.62165.02
2026.02
89.2120.5849.29
2026.02
89.28575.42
2026.02
85.764.5298.59
2026.02
84.265.7391.4
2026.02
82.558.53120.39
2026.02
77.5125.9249.98
2026.02
65.8378.319.59
2026.02
65.8378.319.59
2026.02
65284.5924.99
2026.02
61.4309.5530.2