Claude Opus 4.6 vs Claude Sonnet 5.5
Claude Opus 4.6 Verdict
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 63.1.
- Claude Opus 4.6 is stronger in human preference, multimodal.
- Claude Sonnet 5.5 (max) is stronger in agents & tools, coding, maths, reasoning, composite, knowledge, long context.
- Claude Sonnet 5.5 (max) is 2.5× cheaper ($4.00 vs $10.00 per 1M blended).
- Claude Sonnet 5.5 (max) streams 3.5× faster (141 vs 40 tokens per second).
| Metric | Claude Opus 4.6 | Claude Sonnet 5.5 (max) |
|---|---|---|
| BenchLeader Index | 63.1 | 67.6 |
| Agents & tools score | 68.9 | 69.5 |
| Coding score | 60.1 | 69.8 |
| Human preference score | 64.4 | – |
| Maths score | 68.0 | 72.9 |
| Multimodal score | 66.4 | – |
| Reasoning score | 62.0 | 81.1 |
| Composite score | – | 72.6 |
| Knowledge score | – | 65.4 |
| Long context score | – | 66.6 |
| Blended price $/M | $10.00 | $4.00 |
| Output speed | 40 tok/s | 141 tok/s |
| Time to first answer | 1.6 s | 487.1 s |
| Context window | 1M | 1M |
| GPQA Diamond | 90.5% | 95.6% |
| FrontierMath Tiers 1–3 | – | 88.8% |
| FrontierMath Tier 4 | – | 80.5% |
| OTIS Mock AIME | 94.4% | 100.0% |
| SWE-bench Verified (Epoch) | 78.7% | – |
| SimpleQA Verified | – | 46.5% |
| Humanity's Last Exam | 19.0% | – |
| Terminal-Bench | 79.8% | 61.8% |
| SimpleBench | 67.6% | – |
| SciCode | – | 61.0% |
| Cybench | 93.0% | – |
| Remote Labor Index | 4.2% | – |
| WeirdML | 77.9% | – |
| APEX-Agents | – | 75.5% |
| FrontierCode | 26.6% | – |
| ProofBench | – | 100.0% |
| GSO-Bench | 33.3% | – |
| Epoch Capabilities Index | 155.2 | – |
| LMArena Text | 1498 | – |
| LMArena Hard Prompts | 1527 | – |
| LMArena Coding | 1548 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1313 | – |
| LMArena Agent | – | 12 |
| LiveBench | – | 75.7% |
| LiveBench Reasoning | – | 91.6% |
| LiveBench Coding | – | 91.4% |
| LiveBench Agentic Coding | – | 56.3% |
| LiveBench Mathematics | – | 96.1% |
| LiveBench Data Analysis | – | 59.5% |
| LiveBench Language | – | 78.0% |
| LiveBench Instruction Following | – | 56.8% |
| AA Intelligence Index v4.3.2 | – | 56 |
| AA-LCR | – | 82.7% |
| AA-Omniscience | – | 32.3 |
| Humanity's Last Exam (AA) | – | 55.0% |
| SciCode (AA) | – | 61.0% |
| HiL-Bench | 38.3% | – |
| EQ-Bench 4 | 1223 | – |
| Kagi LLM Benchmark | 72.4% | – |
| SWE-bench Verified (bash only) | 75.6% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
| CritPt | – | 31.4% |
| GDPval-AA v2.1 | – | 67.0% |
| Analyst Agent (AA) | – | 57.5% |
| MedCode | 48.2% | – |
| MedScribe | 86.7% | – |
| Vibe Code Bench v1.1 | 57.6% | – |
| SWE Atlas: Codebase QnA | 33.3% | – |
| SWE Atlas: Refactoring | 35.6% | – |
| SWE Atlas: Test Writing | 36.7% | – |
| LMArena Maths | 1507 | – |
| LMArena Creative Writing | 1479 | – |
| LMArena Instruction Following | 1500 | – |
| LMArena Multi-turn | 1512 | – |
| LMArena Longer Queries | 1517 | – |
| LMArena Document | 1494 | – |
| Chess Puzzles | 17.0% | – |
| Mystery Game Puzzles | 15.0% | 65.0% |
| CL-bench | 20.7% | – |
| CL-bench Life | 13.6% | – |
| METR Time Horizons | 78.9% | – |
| ForecastBench | 60.0% | – |
| CursorBench | – | 55.5% |
| GBAEval | 44.1% | – |
| ALE-Bench | 996.5 | – |
| Vending-Bench 2 | 8017.6 | – |
| FrontierSWE | – | 61.9% |
| Terminal-Bench 4.0 (AA) | – | 63.6% |
| AutomationBench | – | 71.8% |
| GDP.pdf | – | 25.8% |
| MLCR | – | 75.0% |
| Harvey LAB | – | 2.8% |
| AA-Omniscience: accuracy | – | 54.0% |
| AA-Omniscience: non-hallucination | – | 53.0% |
| AA-Briefcase v1.1 | – | 1823 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.6 vs Claude Sonnet 5.5: questions
- Is Claude Opus 4.6 better than Claude Sonnet 5.5?
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 63.1. The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5.5 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Opus 4.6 better than Claude Sonnet 5.5 for coding?
- Claude Sonnet 5.5 scores higher in coding (70 vs 60 on the category index, where 50 is average).
- Is Claude Opus 4.6 better than Claude Sonnet 5.5 for agentic tasks?
- Claude Sonnet 5.5 scores higher in agentic tasks (70 vs 69 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.6 or Claude Sonnet 5.5?
- Claude Sonnet 5.5 is cheaper: $4.00 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.6 or Claude Sonnet 5.5?
- Claude Sonnet 5.5 streams faster: 141 against 40 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.