List your company

Error Recognition on Math500

57.1Top-1 AccuracyCORRECT
8.32420.98733.6546.313Sep 28, 2025

Evaluation results

MethodLinks
CORRECTSynthesized by=GPT-4o-mini2025.0957.187.895.9
CORRECTSynthesized by=GPT-5-Nano2025.0957.187.895.9
BaselineSynthesized by=GPT-5-Nano2025.0941.857.164.3
LLM-as-a-JudgeSynthesized by=GPT-4o-mini2025.0910.223.435.6