Claude Opus 4.6 vs GPT-5 Pro
Claude Opus 4.6 
GPT-5 Pro Verdict
- Claude Opus 4.6 leads on quality: 63.3 vs 60.8.
- Claude Opus 4.6 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, maths, reasoning.
- GPT-5 Pro is stronger in multimodal.
- Claude Opus 4.6 is 4.1× cheaper ($10.00 vs $41.25 per 1M blended).
| Metric | Claude Opus 4.6 | GPT-5 Pro |
|---|---|---|
| BenchLeader Index | 63.3 | 60.8 |
| Agents & tools score | 68.8 | – |
| Coding score | 62.4 | – |
| Composite score | 69.4 | – |
| Human preference score | 64.9 | – |
| Instruction following score | 53.9 | – |
| Knowledge score | 70.6 | 68.0 |
| Long context score | 65.5 | – |
| Maths score | 65.7 | – |
| Multimodal score | 63.6 | 67.4 |
| Reasoning score | 62.6 | 57.6 |
| Blended price $/M | $10.00 | $41.25 |
| Output speed | 36 tok/s | – |
| Time to first answer | 2.4 s | – |
| Context window | 1M | 400k |
| GPQA Diamond | 90.5% | – |
| OTIS Mock AIME | 94.4% | – |
| SWE-bench Verified (Epoch) | 78.7% | – |
| Humanity's Last Exam | 19.0% | 31.6% |
| Terminal-Bench | 79.8% | – |
| SimpleBench | 67.6% | 61.6% |
| Cybench | 93.0% | – |
| Remote Labor Index | 4.2% | – |
| WeirdML | 77.9% | – |
| APEX-Agents | 32.4% | – |
| FrontierCode | 26.6% | – |
| GSO-Bench | 33.3% | – |
| Epoch Capabilities Index | 155.3 | 150.3 |
| LMArena Text | 1498 | – |
| LMArena Hard Prompts | 1527 | – |
| LMArena Coding | 1546 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1311 | – |
| AA Intelligence Index | 31.9 | – |
| IFBench | 53.1% | – |
| AA-LCR | 78.0% | – |
| MMMU-Pro | 75.4% | – |
| AA-Omniscience | 13.7 | – |
| Terminal-Bench Hard | 48.5% | – |
| GPQA Diamond (AA) | 89.6% | – |
| Humanity's Last Exam (AA) | 39.9% | – |
| τ²-Bench Telecom (AA) | 92.1% | – |
| PRBench Finance | – | 51.1% |
| PRBench Legal | – | 49.9% |
| VISTA | – | 52.4% |
| MultiNRC | – | 65.2% |
| HiL-Bench | 38.3% | – |
| EQ-Bench 4 | 1223 | – |
| Kagi LLM Benchmark | 72.4% | 76.8% |
| SWE-bench Verified (bash only) | 75.6% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
| ARC-AGI-1 | – | 70.2% |
| ARC-AGI-2 | – | 18.3% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.6 vs GPT-5 Pro: questions
- Is Claude Opus 4.6 better than GPT-5 Pro?
- Claude Opus 4.6 leads on quality: 63.3 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Claude Opus 4.6 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Which is cheaper, Claude Opus 4.6 or GPT-5 Pro?
- Claude Opus 4.6 is cheaper: $10.00 against $41.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Claude Opus 4.6 accepts more context: 1M against 400k tokens.