List your company

Mathematical Reasoning on AIME 2024 (Pass@1, Pass@128, Weighted Accuracy)

83.33Weighted AccuracyOTV
42.655653.215363.77574.3347Mar 1, 2026

Evaluation results

MethodLinks
OTVBackbone=QWEN3-4B2026.0383.33——
GenRMBackbone=QWEN3-4B2026.0379.11——
Qwen2.5-PRM-7BBackbone=QWEN3-4B2026.0378.18——
DeepConfBackbone=QWEN3-4B2026.0377.76——
VersaPRM-8BBackbone=QWEN3-4B2026.0375.52——
MAJ@128Backbone=QWEN3-4B2026.0375.42——
Qwen2.5-PRM800K-7BBackbone=QWEN3-4B2026.0375.16——
Math-Shepherd-7BBackbone=QWEN3-4B2026.0374.27——
OTVBackbone=DAPO-QWEN-32B2026.0370.83——
AceMath-RM-7BBackbone=QWEN3-4B2026.0367.66——
Qwen2.5-PRM-7BBackbone=DAPO-QWEN-32B2026.0367.45——
Qwen2.5-PRM800K-7BBackbone=DAPO-QWEN-32B2026.0367.03——
VersaPRM-8BBackbone=DAPO-QWEN-32B2026.0366.98——
DeepConfBackbone=DAPO-QWEN-32B2026.0366.77——
MAJ@128Backbone=DAPO-QWEN-32B2026.0366.72——
GenRMBackbone=DAPO-QWEN-32B2026.0366.72——
Math-Shepherd-7BBackbone=DAPO-QWEN-32B2026.0365.73——
AceMath-RM-7BBackbone=DAPO-QWEN-32B2026.0361.15——
OTVBackbone=QWEN3-8B2026.0346.56——
DeepConfBackbone=QWEN3-8B2026.0345.73——
Qwen2.5-PRM-7BBackbone=QWEN3-8B2026.0345.1——
AceMath-RM-7BBackbone=QWEN3-8B2026.0344.9——
VersaPRM-8BBackbone=QWEN3-8B2026.0344.48——
GenRMBackbone=QWEN3-8B2026.0344.38——
MAJ@128Backbone=QWEN3-8B2026.0344.22——
Math-Shepherd-7BBackbone=QWEN3-8B2026.0344.22——
Qwen2.5-PRM800K-7BBackbone=QWEN3-8B2026.0344.22——
Pass@1Backbone=QWEN3-4B2026.03——60.29
Pass@1Backbone=QWEN3-8B2026.03——26.29
Pass@1Backbone=DAPO-QWEN-32B2026.03——51.77
Pass@128Backbone=QWEN3-4B2026.03—91.46—
Pass@128Backbone=QWEN3-8B2026.03—69.58—
Pass@128Backbone=DAPO-QWEN-32B2026.03—83.75—