Claude Opus 4.6 vs Kimi K3
Claude Opus 4.6 
Kimi K3 Verdict
- Kimi K3 leads on quality: 66.5 vs 63.1.
- Claude Opus 4.6 is stronger in agents & tools, instruction following, knowledge, reasoning.
- Kimi K3 is stronger in coding, composite, human preference, long context, maths, multimodal.
- Kimi K3 is 1.7× cheaper ($6.00 vs $10.00 per 1M blended).
| Metric | Claude Opus 4.6 | Kimi K3 |
|---|---|---|
| BenchLeader Index | 63.1 | 66.5 |
| Agents & tools score | 68.8 | 67.5 |
| Coding score | 62.3 | 64.9 |
| Composite score | 69.2 | 74.1 |
| Human preference score | 64.6 | 71.2 |
| Instruction following score | 53.7 | – |
| Knowledge score | 70.5 | 68.1 |
| Long context score | 65.5 | 71.1 |
| Maths score | 65.6 | 78.1 |
| Multimodal score | 63.6 | 65.1 |
| Reasoning score | 62.3 | – |
| Blended price $/M | $10.00 | $6.00 |
| Output speed | 38 tok/s | 37 tok/s |
| Time to first answer | 2.0 s | 57.7 s |
| Context window | 1M | 1.0M |
| GPQA Diamond | 90.5% | – |
| OTIS Mock AIME | 94.4% | – |
| SWE-bench Verified (Epoch) | 78.7% | – |
| Humanity's Last Exam | 19.0% | – |
| Terminal-Bench | 79.8% | – |
| SimpleBench | 67.6% | – |
| SciCode | – | 58.7% |
| Cybench | 93.0% | – |
| Remote Labor Index | 4.2% | – |
| WeirdML | 77.9% | – |
| APEX-Agents | 32.4% | 39.3% |
| FrontierCode | 26.6% | 44.2% |
| ProofBench | – | 87.0% |
| GSO-Bench | 33.3% | – |
| Epoch Capabilities Index | 155.3 | 157.6 |
| LMArena Text | 1498 | – |
| LMArena Hard Prompts | 1527 | – |
| LMArena Coding | 1546 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1311 | – |
| LiveBench | – | 79.2% |
| LiveBench Reasoning | – | 90.7% |
| LiveBench Coding | – | 81.5% |
| LiveBench Agentic Coding | – | 62.2% |
| LiveBench Mathematics | – | 84.4% |
| LiveBench Data Analysis | – | 78.7% |
| LiveBench Language | – | 85.5% |
| AA Intelligence Index | 31.9 | 43.8 |
| IFBench | 53.1% | – |
| AA-LCR | 78.0% | 88.7% |
| MMMU-Pro | 75.4% | 80.5% |
| AA-Omniscience | 13.7 | 19.7 |
| Terminal-Bench Hard | 48.5% | – |
| GPQA Diamond (AA) | 89.6% | 93.5% |
| Humanity's Last Exam (AA) | 39.9% | 46.9% |
| SciCode (AA) | – | 59.5% |
| τ²-Bench Telecom (AA) | 92.1% | – |
| LegalBench | – | 86.0% |
| CorpFin | – | 71.6% |
| TaxEval | – | 75.7% |
| Terminal-Bench 2.1 (Vals) | – | 80.9% |
| SWE-bench (Vals) | – | 93.4% |
| GPQA Diamond (Vals) | – | 92.9% |
| Vals Index | – | 57.8 |
| HiL-Bench | 38.3% | – |
| EQ-Bench 4 | 1223 | 1339 |
| Kagi LLM Benchmark | 72.4% | – |
| SWE-bench Verified (bash only) | 75.6% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.