Claude Opus 4.8 vs Kimi K3
Claude Opus 4.8 
Kimi K3 Verdict
- Kimi K3 leads on quality: 66.5 vs 64.7.
- Claude Opus 4.8 is stronger in coding, composite, instruction following, reasoning.
- Kimi K3 is stronger in agents & tools, human preference, knowledge, long context, multimodal, maths.
- Kimi K3 is 1.7× cheaper ($6.00 vs $10.00 per 1M blended).
- Claude Opus 4.8 streams 1.6× faster (58 vs 37 tokens per second).
| Metric | Claude Opus 4.8 | Kimi K3 |
|---|---|---|
| BenchLeader Index | 64.7 | 66.5 |
| Agents & tools score | 65.0 | 67.5 |
| Coding score | 65.7 | 64.9 |
| Composite score | 81.9 | 74.1 |
| Human preference score | 65.6 | 71.2 |
| Instruction following score | 61.6 | – |
| Knowledge score | 66.3 | 68.1 |
| Long context score | 65.3 | 71.1 |
| Multimodal score | 64.4 | 65.1 |
| Reasoning score | 64.2 | – |
| Maths score | – | 78.1 |
| Blended price $/M | $10.00 | $6.00 |
| Output speed | 58 tok/s | 37 tok/s |
| Time to first answer | 29.5 s | 57.7 s |
| Context window | 1M | 1.0M |
| SimpleBench | 64.8% | – |
| SciCode | – | 58.7% |
| Remote Labor Index | 8.3% | – |
| APEX-Agents | – | 39.3% |
| FrontierCode | 46.5% | 44.2% |
| ProofBench | – | 87.0% |
| GSO-Bench | 47.1% | – |
| Epoch Capabilities Index | 158.3 | 157.6 |
| LMArena Text | 1473 | – |
| LMArena Hard Prompts | 1503 | – |
| LMArena Coding | 1527 | – |
| LMArena WebDev | 1540 | – |
| LMArena Vision | 1289 | – |
| 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 | 42.0 | 43.8 |
| IFBench | 62.2% | – |
| AA-LCR | 77.7% | 88.7% |
| MMMU-Pro | – | 80.5% |
| AA-Omniscience | 28.8 | 19.7 |
| Terminal-Bench Hard | 58.3% | – |
| GPQA Diamond (AA) | 92.0% | 93.5% |
| Humanity's Last Exam (AA) | 48.7% | 46.9% |
| SciCode (AA) | 54.4% | 59.5% |
| τ²-Bench Telecom (AA) | 94.4% | – |
| LiveCodeBench | 87.8% | – |
| MMLU-Pro | 89.6% | – |
| LegalBench | 83.6% | 86.0% |
| CorpFin | 66.7% | 71.6% |
| TaxEval | 75.6% | 75.7% |
| Terminal-Bench 2.1 (Vals) | 71.9% | 80.9% |
| SWE-bench (Vals) | 88.6% | 93.4% |
| GPQA Diamond (Vals) | 92.4% | 92.9% |
| Vals Index | 60.9 | 57.8 |
| HiL-Bench | 35.3% | – |
| EQ-Bench 4 | 1281 | 1339 |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.