| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | DeepSeek-V3 | DeepSeek | 69.8 | 1 | 2026-07-06 |
| 2 | Llama 3.1 Instruct 405B | Meta | 59.9 | 1 | 2026-07-06 |
| 3 | Qwen2.5 Instruct 72B | Alibaba | 59.9 | 1 | 2026-07-06 |
| 4 | DeepSeek-V2 | DeepSeek | 49.8 | 1 | 2026-07-06 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.