| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Gemini 3 Deep Think | 83.3 | 1 | 2026-08-23 | |
| 2 | GPT-5 Pro | OpenAI | 77.5 | 1 | 2026-08-23 |
| 3 | Gemini 3 Pro | 75.8 | 1 | 2026-08-23 | |
| 4 | DeepSeek-V3.2-Speciale | DeepSeek | 59.2 | 1 | 2026-08-23 |
| 5 | GPT-5.1 | OpenAI | 48.3 | 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.