| # | Model | Creator | Score |
|---|---|---|---|
| 1 | GPT-5.4 Pro | OpenAI | 92 |
| 2 | Gemini 3.1 Pro | 87 | |
| 3 | Claude Opus 4.6 | Anthropic | 85 |
| 4 | Grok 4.1 | xAI | 85 |
| 5 | GPT-5.3 Codex | OpenAI | 85 |
| 6 | Claude Sonnet 4.6 | Anthropic | 84 |
| 7 | GPT-5.4 | OpenAI | 82 |
| 8 | GLM-5 (Reasoning) | Zhipu AI | 82 |
| 9 | GPT-5.2 | OpenAI | 82 |
| 10 | GPT-5 (high) | OpenAI | 82 |