| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | OpenAI | 94.9 | 1 | 2026-08-23 |
| 2 | GPT-5.4 | OpenAI | 92.5 | 1 | 2026-08-23 |
| 3 | Kimi K3 | Moonshot | 91.3 | 1 | 2026-08-23 |
| 4 | Gemini 3.5 Flash | 89.9 | 1 | 2026-08-23 | |
| 5 | Gemini 3.1 Pro | 89.4 | 1 | 2026-08-23 | |
| 6 | Gemini 3.6 Flash | 87.8 | 1 | 2026-08-23 | |
| 7 | GPT-5.2 | OpenAI | 86.5 | 1 | 2026-08-23 |
| 8 | Gemini 3 Flash Preview | 85.8 | 1 | 2026-08-23 | |
| 9 | Gemini 3 Pro | 84.2 | 1 | 2026-08-23 | |
| 10 | Claude Opus 4.8 | Anthropic | 81.6 | 1 | 2026-08-23 |
| 11 | Kimi K2.5 | Moonshot | 80.6 | 1 | 2026-08-23 |
| 12 | GPT-5 | OpenAI | 78.8 | 1 | 2026-08-23 |
| 13 | GPT-5 mini | OpenAI | 78.2 | 1 | 2026-08-23 |
| 14 | Gemini 2.5 Pro | 77.2 | 1 | 2026-08-23 | |
| 15 | GPT-5.1 | OpenAI | 76.9 | 1 | 2026-08-23 |
| 16 | Claude Sonnet 4.5 | Anthropic | 75.8 | 1 | 2026-08-23 |
| 17 | Claude Opus 4.6 | Anthropic | 72.3 | 1 | 2026-08-23 |
| 18 | Grok 4 | SpaceXAI | 70 | 1 | 2026-08-23 |
| 19 | Grok 4.1 Fast | SpaceXAI | 69 | 1 | 2026-08-23 |
| 20 | GLM-4.5V | Z.ai | 67.6 | 1 | 2026-08-23 |
| 21 | Grok 4 Fast R | SpaceXAI | 66.8 | 1 | 2026-08-23 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.