| # | Model | Creator | Score |
|---|---|---|---|
| 1 | Claude Mythos Preview | Anthropic | 99 |
| 2 | GPT-5.4 | OpenAI | 94 |
| 3 | Gemini 3.1 Pro | 94 | |
| 4 | Claude Opus 4.6 | Anthropic | 92 |
| 5 | GPT-5.4 Pro | OpenAI | 92 |
| 6 | GPT-5.3 Codex | OpenAI | 89 |
| 7 | Gemini 3 Pro Deep Think | 87 | |
| 8 | Claude Sonnet 4.6 | Anthropic | 86 |
| 9 | GLM-5 (Reasoning) | Z.AI | 85 |
| 10 | GLM-5.1 | Z.AI | 84 |