Reasoning on AIME 2026 (Avg@64)
99.17Avg@64OpenAI GPT-5.4
Evaluation Results
| Method | Links | |
|---|---|---|
| OpenAI GPT-5.42026.06 | 99.17 | |
| Gemini 3.1-Pro2026.06 | 98.33 | |
| Claude Opus-4.62026.06 | 96.67 | |
| Claude Opus-4.72026.06 | 96.41 | |
| Kimi-K2.62026.06 | 96.4 | |
| DS-V4-Pro2026.06 | 95.83 | |
| Ring-2.6-1Tvariant=xhigh2026.06 | 95.78 | |
| GLM-5.12026.06 | 95.3 | |
| Ring-2.6-1Tvariant=high2026.06 | 87.86 |