Claude Opus 4.5 vs GPT-5 Pro
Claude Opus 4.5 
GPT-5 Pro Verdict
- Claude Opus 4.5 (thinking) and GPT-5 Pro are level on quality (60.7 vs 60.8).
- Claude Opus 4.5 (thinking) is stronger in agents & tools, coding, composite, instruction following, long context, maths, reasoning.
- GPT-5 Pro is stronger in knowledge, multimodal.
- Claude Opus 4.5 (thinking) is 4.1× cheaper ($10.00 vs $41.25 per 1M blended).
| Metric | Claude Opus 4.5 (thinking) | GPT-5 Pro |
|---|---|---|
| BenchLeader Index | 60.7 | 60.8 |
| Agents & tools score | 74.6 | – |
| Coding score | 56.4 | – |
| Composite score | 65.8 | – |
| Instruction following score | 54.8 | – |
| Knowledge score | 61.0 | 68.0 |
| Long context score | 65.2 | – |
| Maths score | 64.0 | – |
| Multimodal score | 58.0 | 67.4 |
| Reasoning score | 58.6 | 57.6 |
| Blended price $/M | $10.00 | $41.25 |
| Output speed | 45 tok/s | – |
| Time to first answer | 17.3 s | – |
| Context window | 200k | 400k |
| Humanity's Last Exam | – | 31.6% |
| SimpleBench | – | 61.6% |
| Epoch Capabilities Index | – | 150.3 |
| AA Intelligence Index | 29.1 | – |
| IFBench | 58.0% | – |
| AA-LCR | 77.3% | – |
| MMMU-Pro | 74.0% | – |
| AA-Omniscience | 14 | – |
| Terminal-Bench Hard | 47.0% | – |
| GPQA Diamond (AA) | 86.6% | – |
| Humanity's Last Exam (AA) | 30.1% | – |
| τ²-Bench Telecom (AA) | 89.5% | – |
| AIME (Vals) | 95.4% | – |
| LiveCodeBench | 83.7% | – |
| MMLU-Pro | 87.3% | – |
| IOI | 20.3% | – |
| 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% | 51.1% |
| PRBench Legal | 44.2% | 49.9% |
| VISTA | 46.4% | 52.4% |
| MultiNRC | 48.6% | 65.2% |
| TutorBench | 51.2% | – |
| Kagi LLM Benchmark | 80.2% | 76.8% |
| ARC-AGI-1 | 80.0% | 70.2% |
| ARC-AGI-2 | 37.6% | 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 4.5 vs GPT-5 Pro: questions
- Is Claude Opus 4.5 better than GPT-5 Pro?
- Claude Opus 4.5 (thinking) and GPT-5 Pro are level on quality (60.7 vs 60.8). The BenchLeader Index combines every independent quality benchmark; GPT-5 Pro is ahead overall as of 2026-09-10, but check the category scores for your use.
- Which is cheaper, Claude Opus 4.5 or GPT-5 Pro?
- Claude Opus 4.5 is cheaper: $10.00 against $41.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- GPT-5 Pro accepts more context: 400k against 200k tokens.