List your company

Mathematical Reasoning on MATH500 (Accuracy, Steps, and Speed)

45.4AccuracyCOVER
29.59233.69637.841.904Feb 5, 2026

Evaluation results

MethodLinks
COVERBackbone=Dream-Ins-7B, Length=5122026.0245.4143.912.95
SaberBackbone=Dream-Ins-7B, Length=5122026.0245352.111.59
WINOBackbone=Dream-Ins-7B, Length=5122026.0244.4204.582.38
COVERBackbone=Dream-Ins-7B, Length=2562026.0243.6105.31.84
COVERBackbone=LLaDA-1.5-8B, Length=5122026.0242.6111.052.82
WINOBackbone=Dream-Ins-7B, Length=2562026.0242.4139.641.77
baselineBackbone=Dream-Ins-7B, Length=5122026.0242.45121
SaberBackbone=Dream-Ins-7B, Length=2562026.0242172.761.56
WINOBackbone=LLaDA-1.5-8B, Length=5122026.0241.4122.322.59
SaberBackbone=LLaDA-1.5-8B, Length=5122026.0241213.552.37
COVERBackbone=LLaDA-Ins-8B, Length=5122026.0240.899.973.62
baselineBackbone=LLaDA-1.5-8B, Length=5122026.02405121
baselineBackbone=Dream-Ins-7B, Length=2562026.02402561
WINOBackbone=LLaDA-Ins-8B, Length=5122026.0239.2115.692.33
SaberBackbone=LLaDA-Ins-8B, Length=5122026.0238.2170.122.92
baselineBackbone=LLaDA-Ins-8B, Length=5122026.0236.95121
COVERBackbone=LLaDA-1.5-8B, Length=2562026.023666.172.66
SaberBackbone=LLaDA-1.5-8B, Length=2562026.0235.8132.512.34
baselineBackbone=LLaDA-1.5-8B, Length=2562026.0235.22561
WINOBackbone=LLaDA-1.5-8B, Length=2562026.0234.696.732.05
COVERBackbone=LLaDA-Ins-8B, Length=2562026.0232.868.052.52
COVERBackbone=LLaDA-Base-8B, Length=5122026.0232.4124.292.91
WINOBackbone=LLaDA-Ins-8B, Length=2562026.0232.475.491.96
COVERBackbone=LLaDA-Base-8B, Length=2562026.023287.662.08
SaberBackbone=LLaDA-Base-8B, Length=2562026.0231.8123.912.02
baselineBackbone=LLaDA-Base-8B, Length=5122026.0231.85121
SaberBackbone=LLaDA-Ins-8B, Length=2562026.0231.8130.662.25
WINOBackbone=LLaDA-Base-8B, Length=5122026.0231.6139.451.76
WINOBackbone=LLaDA-Base-8B, Length=2562026.0230.8102.31.16
baselineBackbone=LLaDA-Base-8B, Length=2562026.0230.62561
baselineBackbone=LLaDA-Ins-8B, Length=2562026.0230.52561
SaberBackbone=LLaDA-Base-8B, Length=5122026.0230.2181.982.8