List your company

Mathematical Reasoning on BIGMATH (Competition Subsets and Pass@8)

49.95MATH500 ScoreRLVR
36.710840.147943.58547.0221Oct 10, 2025

Evaluation results

MethodLinks
RLVRBackbone=LLAMA-3.1-8B-INSTRUCT2025.1049.9553.3326.2518.131.2517.3237.31
RLERBackbone=LLAMA-3.1-8B-INSTRUCT, k=2, Gk=82025.1048.354.172.9223.7516.671.2516.1935.07
INTUITORBackbone=LLAMA-3.1-8B-INSTRUCT, Category=RLIR2025.1046.253.332.521.5612.780.4214.4731.72
pre-RLBackbone=LLAMA-3.1-8B-INSTRUCT2025.1045.753.75019.3812.22013.5230.2
SCBackbone=LLAMA-3.1-8B-INSTRUCT, Category=RLIR2025.1042.652.52.0824.3712.78014.0630.85
JudgeBackbone=LLAMA-3.1-8B-INSTRUCT, Category=RLIR2025.1037.220.421.2515.6210.83010.8925.39