Claude Opus 4.5 vs GPT-5
Claude Opus 4.5 
GPT-5 Verdict
- Claude Opus 4.5 (thinking) and GPT-5 are level on quality (61.1 vs 60.8).
- Claude Opus 4.5 (thinking) is stronger in agents & tools, composite.
- GPT-5 is stronger in coding, instruction following, knowledge, long context, maths, multimodal, reasoning, human preference.
- GPT-5 is 2.9× cheaper ($3.44 vs $10.00 per 1M blended).
- GPT-5 streams 1.8× faster (85 vs 46 tokens per second).
| Metric | Claude Opus 4.5 (thinking) | GPT-5 |
|---|---|---|
| BenchLeader Index | 61.1 | 60.8 |
| Agents & tools score | 74.6 | 51.0 |
| Coding score | 60.5 | 60.9 |
| Composite score | 65.8 | 58.1 |
| Instruction following score | 54.8 | 65.0 |
| Knowledge score | 61.0 | 62.2 |
| Long context score | 65.2 | 65.6 |
| Maths score | 64.0 | 72.8 |
| Multimodal score | 58.0 | 59.6 |
| Reasoning score | 58.6 | 64.2 |
| Human preference score | – | 61.7 |
| Blended price $/M | $10.00 | $3.44 |
| Output speed | 46 tok/s | 85 tok/s |
| Time to first answer | 16.3 s | 60.7 s |
| Context window | 200k | 400k |
| Terminal-Bench | – | 49.6% |
| SciCode | – | 42.9% |
| Remote Labor Index | – | 1.7% |
| WeirdML | – | 39.8% |
| APEX-Agents | – | 18.3% |
| Epoch Capabilities Index | – | 150 |
| LMArena Text | – | 1427 |
| LMArena Hard Prompts | – | 1449 |
| LMArena Coding | – | 1462 |
| LMArena Vision | – | 1232 |
| AA Intelligence Index | 29.1 | 23.0 |
| IFBench | 58.0% | 73.1% |
| AA-LCR | 77.3% | 78.2% |
| MMMU-Pro | 74.0% | 74.2% |
| AA-Omniscience | 14 | -8.7 |
| Terminal-Bench Hard | 47.0% | 32.6% |
| GPQA Diamond (AA) | 86.6% | 85.3% |
| Humanity's Last Exam (AA) | 30.1% | 28.5% |
| τ²-Bench Telecom (AA) | 89.5% | 84.8% |
| AIME (Vals) | 95.4% | – |
| LiveCodeBench | 83.7% | – |
| MMLU-Pro | 87.3% | – |
| LegalBench | 84.6% | – |
| CorpFin | 65.1% | – |
| TaxEval | 74.9% | – |
| MedQA | 95.9% | – |
| MGSM | 95.2% | – |
| SWE-bench (Vals) | 76.4% | – |
| GPQA Diamond (Vals) | 85.9% | – |
| MultiChallenge | 59.0% | – |
| PRBench Finance | 46.2% | 51.3% |
| PRBench Legal | 44.2% | 49.0% |
| VISTA | 46.4% | 49.7% |
| MultiNRC | 48.6% | 52.1% |
| TutorBench | 51.2% | 55.3% |
| Kagi LLM Benchmark | 80.2% | 72.7% |
| IFEval (HELM) | – | 87.5% |
| Omni-MATH (HELM) | – | 64.7% |
| WildBench (HELM) | – | 85.7% |
| MMLU-Pro (HELM) | – | 86.3% |
| GPQA Diamond (HELM) | – | 79.1% |
| HELM Capabilities mean | – | 80.7% |
| Aider Polyglot | – | 88.0% |
| SWE-bench Verified (any scaffold) | – | 75.6% |
| ARC-AGI-1 | 80.0% | – |
| ARC-AGI-2 | 37.6% | – |
Data as of 2026-09-12. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.5 vs GPT-5: questions
- Is Claude Opus 4.5 better than GPT-5?
- Claude Opus 4.5 (thinking) and GPT-5 are level on quality (61.1 vs 60.8). The BenchLeader Index combines every independent quality benchmark; Claude Opus 4.5 (thinking) is ahead overall as of 2026-09-12, but check the category scores for your use.
- Is Claude Opus 4.5 better than GPT-5 for coding?
- GPT-5 scores higher in coding (61 vs 61 on the category index, where 50 is average).
- Is Claude Opus 4.5 better than GPT-5 for agentic tasks?
- Claude Opus 4.5 scores higher in agentic tasks (75 vs 51 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.5 or GPT-5?
- GPT-5 is cheaper: $3.44 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.5 or GPT-5?
- GPT-5 streams faster: 85 against 46 output tokens per second.
- Which has the larger context window?
- GPT-5 accepts more context: 400k against 200k tokens.