| Benchmark | Kimi K2.6 | Llama 3.1 Instruct 405B |
|---|---|---|
| AA Agentic Index | 58.7 | 6.3 |
| AA Intelligence | 45.1 | 8.5 |
| AA-LCR | 76.7 | 24.7 |
| AA-Omniscience | 6.4 | -17.1 |
| Artificial Analysis Coding Index | 61.8 | 14.5 |
| Chinese SimpleQA (C-SimpleQA) | 75.9 | 54.7 |
| critpt | 8 | 0 |
| gdpval | 41.4 | 0 |
| GPQA Diamond | 91.1 | 51.5 |
| HLE | 37.5 | 4.2 |
| IFBench | 76 | 39 |
| LiveCodeBench | 89.6 | 30.1 |
| MMLU-Pro | 87.1 | 73.4 |
| OmniScience Accuracy | 32.8 | 23.2 |
| OmniScience Non-Hallucination | 60.7 | 49 |
| scicode | 53.5 | 29.9 |
| SWE-bench Pro | 58.6 | 11.2 |
| SWE-bench Verified | 80.2 | 24.5 |
| Terminal-Bench Hard | 43.9 | 6.8 |
| τ²-Bench Telecom (AA run) | 95.9 | 19 |
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.