| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | Proprietary | 49.7% | |
| 2 | Claude Fable 5.1 | Anthropic | Proprietary | 41.9% | |
| 3 | Claude Fable 5 | Anthropic | Proprietary | 38.6% | |
| 4 | Gemini 3.8 Flash | Google · Closed | 38.6% | ||
| 5 | GPT-5.5 | OpenAI · Closed | 36.2% | ||
| 6 | Gemini 3.5 Flash | Google · Closed | 33.6% | ||
| 7 | GPT-5.6 Sol | OpenAI · Closed | 33.6% | ||
| 8 | Grok 4.6 | xAI · Closed | 33.2% | ||
| 9 | Gemini 3.6 Flash | Google · Closed | 31.2% | ||
| 10 | GPT-5.6 Terra | OpenAI · Closed | 30.8% | ||
| 11 | Claude Opus 5 | Anthropic · Closed | 30.4% | ||
| 12 | Kimi K3 | Moonshot AI · Closed | 29.5% | ||
| 13 | Grok 4.5 | xAI · Closed | 27.3% | ||
| 14 | GPT-5.4 | OpenAI · Closed | 27.1% | ||
| 15 | Gemini 3.1 Pro | Google · Closed | 26.5% | ||
| 16 | Claude Sonnet 5 | Anthropic · Closed | 24.9% | ||
| 17 | Claude Opus 4.7 | Anthropic · Closed | 24.5% | ||
| 18 | GPT-5.6 Luna | OpenAI · Closed | 22.6% | ||
| 19 | Claude Opus 4.8 | Anthropic · Closed | 14.5% | ||
| 20 | Claude Sonnet 4.6 | Anthropic · Closed | 6.7% | ||
| 21 | Kimi K2.6 | Moonshot AI · Open weight | 3.9% | ||
| 22 | Gemini 3 Flash | Google · Closed | 0.0% | ||
| 23 | Grok 4.3 | xAI · Closed | 0.0% | ||
| 24 | Gemini Robotics-ER 1.6 | 0.0% | |||
| 25 | Claude Haiku 4.5 | Anthropic · Closed | 0.0% | ||
| 26 | Grok 4.20 | xAI · Closed | 0.0% |