List your company

Math Evaluation on Math ID

97.26AccuracyGPT-5.2-chat-latest
88.659290.892193.12595.3579May 20, 2026

Evaluation results

MethodLinks
GPT-5.2-chat-latest2026.0597.2680.53
GPT-5-chat-latest2026.0596.9475.22
GSPO+AIR2026.0594.9368.14
GRPO2026.0593.8164.6
GRPO+AIR2026.0593.6463.72
GSPO2026.0593.5665.49
GRPO+V-REx2026.0593.0260.71
Llama-4-Maverick2026.0592.8461.06
GSPO+V-REx2026.0592.7758.94
Qwen-3-14B2026.0592.2858.41
Gemini-3-Pro-Preview2026.0590.0233.63
Gemini-2.5-Pro2026.0589.6237.17
Qwen-2.5-14B-Instruct2026.0588.9948.67