| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 (xHigh) | Anthropic | Closed | 7.34x | |
| 2 | GPT-5.4 (High) | OpenAI | Closed | 6.16x | |
| 3 | Claude Sonnet 4.6 | Anthropic | Closed | 5.56x | |
| 4 | GPT-5.3 Codex (High) | OpenAI · Closed | 5.49x | ||
| 5 | GPT-5.5 (xHigh) | OpenAI · Closed | 5.45x | ||
| 6 | Gemini 3.1 Pro | Google · Closed | 4.92x | ||
| 7 | Kimi K2.6 | Moonshot AI · Open weight | 4.51x | ||
| 8 | Claude Opus 4.6 | Anthropic · Closed | 4.38x | ||
| 9 | GPT-5.2 | OpenAI · Closed | 4.28x | ||
| 11 | Gemini 3.5 Flash | Google · Closed | 4.16x | ||
| 12 | Claude Opus 4.5 | Anthropic · Closed | 3.76x | ||
| 13 | GPT-5.1 Codex Max | OpenAI · Closed | 3.59x | ||
| 14 | GLM-5 | Z.AI · Open weight | 3.22x | ||
| 15 | Claude Sonnet 4.5 | Anthropic · Closed | 3.18x | ||
| 16 | Claude Haiku 4.5 | Anthropic · Closed | 2.78x | ||
| 18 | GPT-5.2 Codex | OpenAI · Closed | 1.98x |