| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | GPT-5.6 Luna | OpenAI | 84 | 1 | 2026-07-30 |
| 2 | Qwen3.5 397B A17B | Alibaba | 78.6 | 1 | 2026-07-30 |
| 3 | Inkling-Small | Thinking Machines | 77.4 | 1 | 2026-07-30 |
| 4 | Inkling | Thinking Machines | 77.1 | 1 | 2026-07-30 |
| 5 | MiniMax M2.7 | MiniMax | 76.3 | 1 | 2026-07-30 |
| 6 | DeepSeek-V4-Flash | DeepSeek | 73.2 | 1 | 2026-07-30 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.