Claude Opus 4.5 vs Kimi K2.6
Claude Opus 4.5 
Kimi K2.6 Verdict
- Claude Opus 4.5 (thinking) and Kimi K2.6 are level on quality (60.7 vs 60.7).
- Claude Opus 4.5 (thinking) is stronger in agents & tools, knowledge, maths.
- Kimi K2.6 is stronger in coding, composite, instruction following, long context, multimodal, reasoning, human preference.
- Kimi K2.6 is 5.8× cheaper ($1.71 vs $10.00 per 1M blended).
| Metric | Claude Opus 4.5 (thinking) | Kimi K2.6 |
|---|---|---|
| BenchLeader Index | 60.7 | 60.7 |
| Agents & tools score | 74.6 | 45.1 |
| Coding score | 56.4 | 60.4 |
| Composite score | 65.8 | 68.6 |
| Instruction following score | 54.8 | 73.7 |
| Knowledge score | 61.0 | 58.6 |
| Long context score | 65.2 | 67.1 |
| Maths score | 64.0 | 53.8 |
| Multimodal score | 58.0 | 63.7 |
| Reasoning score | 58.6 | 66.0 |
| Human preference score | – | 60.8 |
| Blended price $/M | $10.00 | $1.71 |
| Output speed | 45 tok/s | 44 tok/s |
| Time to first answer | 17.3 s | 103.2 s |
| Context window | 200k | 262k |
| GPQA Diamond | – | 90.8% |
| FrontierMath Tiers 1–3 | – | 57.2% |
| FrontierMath Tier 4 | – | 25.6% |
| OTIS Mock AIME | – | 96.1% |
| SWE-bench Verified (Epoch) | – | 76.7% |
| SimpleQA Verified | – | 34.9% |
| OSWorld-Verified 2.0 | – | 4.6% |
| SciCode | – | 53.5% |
| WeirdML | – | 55.9% |
| APEX-Agents | – | 18.9% |
| ProofBench | – | 16.0% |
| Epoch Capabilities Index | – | 151.0 |
| LMArena Text | – | 1461 |
| LMArena Hard Prompts | – | 1485 |
| LMArena Coding | – | 1514 |
| LMArena WebDev | – | 1509 |
| LMArena Vision | – | 1281 |
| AA Intelligence Index | 29.1 | 31.3 |
| IFBench | 58.0% | 76.0% |
| AA-LCR | 77.3% | 81.0% |
| MMMU-Pro | 74.0% | 79.4% |
| AA-Omniscience | 14 | 5.3 |
| Terminal-Bench Hard | 47.0% | 43.9% |
| GPQA Diamond (AA) | 86.6% | 91.1% |
| Humanity's Last Exam (AA) | 30.1% | 37.5% |
| SciCode (AA) | – | 51.5% |
| τ²-Bench Telecom (AA) | 89.5% | 95.9% |
| AIME (Vals) | 95.4% | – |
| LiveCodeBench | 83.7% | 86.8% |
| MMLU-Pro | 87.3% | 87.6% |
| IOI | 20.3% | – |
| LegalBench | 84.6% | 84.7% |
| CorpFin | 65.1% | 66.7% |
| TaxEval | 74.9% | 74.7% |
| MedQA | 95.9% | – |
| MGSM | 95.2% | – |
| Terminal-Bench 2.1 (Vals) | – | 53.6% |
| SWE-bench (Vals) | 76.4% | 76.2% |
| GPQA Diamond (Vals) | 85.9% | 89.1% |
| Vals Index | – | 43.5 |
| MultiChallenge | 59.0% | – |
| PRBench Finance | 46.2% | – |
| PRBench Legal | 44.2% | – |
| VISTA | 46.4% | – |
| MultiNRC | 48.6% | – |
| HiL-Bench | – | 18.7% |
| TutorBench | 51.2% | – |
| EQ-Bench 4 | – | 1202 |
| Kagi LLM Benchmark | 80.2% | – |
| ARC-AGI-1 | 80.0% | – |
| ARC-AGI-2 | 37.6% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.5 vs Kimi K2.6: questions
- Is Claude Opus 4.5 better than Kimi K2.6?
- Claude Opus 4.5 (thinking) and Kimi K2.6 are level on quality (60.7 vs 60.7). The BenchLeader Index combines every independent quality benchmark; Kimi K2.6 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Opus 4.5 better than Kimi K2.6 for coding?
- Kimi K2.6 scores higher in coding (60 vs 56 on the category index, where 50 is average).
- Is Claude Opus 4.5 better than Kimi K2.6 for agentic tasks?
- Claude Opus 4.5 scores higher in agentic tasks (75 vs 45 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.5 or Kimi K2.6?
- Kimi K2.6 is cheaper: $1.71 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.5 or Kimi K2.6?
- Claude Opus 4.5 streams faster: 45 against 44 output tokens per second.
- Which has the larger context window?
- Kimi K2.6 accepts more context: 262k against 200k tokens.