List your company

Math Reasoning on AIME 2025 (Score)

100ScoreGPT-5.2
24.423244.044163.66583.2859Mar 26, 2026Apr 5, 2026Apr 15, 2026Apr 26, 2026May 6, 2026May 16, 2026May 27, 2026

Evaluation results

MethodLinks
GPT-5.22026.03100
Kimi-K2.5Number of Parameters=1T-A32B2026.0396.1
Gemini-3-Pro2026.0395
Intern-S1-ProNumber of Parameters=1T-A22B2026.0393.1
Qwen3-VL-235B-ThinkingNumber of Parameters=235B-A22B, Thinking Configuration=true2026.0390
Soft-RLVRVerifier=GPT-OSS-20B, Checklist source=DeepSeek R1, Training step=5002026.0528.67
Soft-RLVRVerifier=GPT-OSS-120B, Checklist source=DeepSeek R1, Training step=5002026.0528.5
Oracle rule-basedReward=Oracle rule-based, Training step=5002026.0528
Command R7B (No RL)Reward=None (Initial Policy), Training step=5002026.0527.33