Claude Opus 4.1 vs GPT-5.4 Pro
Claude Opus 4.1 
GPT-5.4 Pro Verdict
- GPT-5.4 Pro leads on quality: 64.3 vs 57.2.
- Claude Opus 4.1 (thinking) is stronger in coding, human preference, maths.
- GPT-5.4 Pro is stronger in instruction following, knowledge, multimodal, reasoning.
- Claude Opus 4.1 (thinking) is 2.3× cheaper ($30.00 vs $67.50 per 1M blended).
- Claude Opus 4.1 (thinking) streams 10.5× faster (11 vs 1 tokens per second).
| Metric | Claude Opus 4.1 (thinking) | GPT-5.4 Pro |
|---|---|---|
| BenchLeader Index | 57.2 | 64.3 |
| Coding score | 53.3 | – |
| Human preference score | 64.5 | – |
| Instruction following score | 50.4 | 67.3 |
| Knowledge score | 58.3 | 73.6 |
| Maths score | 59.3 | – |
| Multimodal score | 60.9 | 69.8 |
| Reasoning score | 65.6 | 75.3 |
| Blended price $/M | $30.00 | $67.50 |
| Output speed | 11 tok/s | 1 tok/s |
| Time to first answer | 3.2 s | 6.3 s |
| Context window | 200k | 1.1M |
| Humanity's Last Exam | – | 44.3% |
| SimpleBench | – | 74.1% |
| Epoch Capabilities Index | – | 158.9 |
| LMArena Text | 1450 | – |
| LMArena Hard Prompts | 1480 | – |
| LMArena Coding | 1512 | – |
| AIME (Vals) | 78.2% | – |
| LiveCodeBench | 66.5% | – |
| MMLU-Pro | 87.9% | – |
| TaxEval | 73.7% | – |
| MedQA | 93.6% | – |
| MGSM | 94.4% | – |
| GPQA Diamond (Vals) | 76.3% | – |
| MultiChallenge | 57.2% | 69.2% |
| VISTA | 48.4% | 53.9% |
| MultiNRC | 38.4% | 62.3% |
| TutorBench | 50.8% | 56.6% |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.1 vs GPT-5.4 Pro: questions
- Is Claude Opus 4.1 better than GPT-5.4 Pro?
- GPT-5.4 Pro leads on quality: 64.3 vs 57.2. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 Pro is ahead overall as of 2026-09-13, but check the category scores for your use.
- Which is cheaper, Claude Opus 4.1 or GPT-5.4 Pro?
- Claude Opus 4.1 is cheaper: $30.00 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.1 or GPT-5.4 Pro?
- Claude Opus 4.1 streams faster: 11 against 1 output tokens per second.
- Which has the larger context window?
- GPT-5.4 Pro accepts more context: 1.1M against 200k tokens.