| Benchmark | Kimi K2.6 | o1 |
|---|---|---|
| AA Agentic Index | 58.7 | 31.1 |
| AA Intelligence | 45.1 | 24 |
| AA-LCR | 76.7 | 63.3 |
| AA-Omniscience | 6.4 | -10.6 |
| arena_vision | 1264 | 1193 |
| Artificial Analysis Coding Index | 61.8 | 39.7 |
| critpt | 8 | 0.3 |
| gdpval | 41.4 | 11.5 |
| GPQA Diamond | 91.1 | 75.7 |
| HLE | 37.5 | 7.7 |
| IFBench | 76 | 70.3 |
| livebench | 72.2 | 52.3 |
| OmniScience Accuracy | 32.8 | 34.7 |
| OmniScience Non-Hallucination | 60.7 | 30.7 |
| scicode | 53.5 | 35.8 |
| strongreject | 99.8 | 97 |
| SWE-bench Verified | 80.2 | 48.9 |
| Terminal-Bench Hard | 43.9 | 12.9 |
| τ²-Bench Telecom (AA run) | 95.9 | 62.6 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.