Reasoning & General Score on AIME 2026 I
93.3AIME Part I ScoreClaude Opus 4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Opus 4.52026.02 | 93.3 | |
| GLM-4.72026.02 | 92.9 | |
| GLM-52026.02 | 92.7 | |
| DeepSeek-V3.22026.02 | 92.7 | |
| Kimi K2.52026.02 | 92.5 | |
| Gemini 3 Pro2026.02 | 90.6 |
Loading the SOTA2 catalog…