Claude Sonnet 5 vs GPT-5.4 Pro
Claude Sonnet 5 
GPT-5.4 Pro Verdict
- GPT-5.4 Pro leads on quality: 64.3 vs 61.4.
- Claude Sonnet 5 (high) is stronger in agents & tools, coding, composite, human preference, long context.
- GPT-5.4 Pro is stronger in knowledge, multimodal, reasoning, instruction following.
- Claude Sonnet 5 (high) is 17× cheaper ($4.00 vs $67.50 per 1M blended).
- Claude Sonnet 5 (high) streams 59.5× faster (60 vs 1 tokens per second).
| Metric | Claude Sonnet 5 (high) | GPT-5.4 Pro |
|---|---|---|
| BenchLeader Index | 61.4 | 64.3 |
| Agents & tools score | 61.8 | – |
| Coding score | 61.6 | – |
| Composite score | 69.5 | – |
| Human preference score | 66.2 | – |
| Knowledge score | 62.4 | 73.6 |
| Long context score | 64.8 | – |
| Multimodal score | 63.1 | 69.8 |
| Reasoning score | 66.8 | 75.3 |
| Instruction following score | – | 67.3 |
| Blended price $/M | $4.00 | $67.50 |
| Output speed | 60 tok/s | 1 tok/s |
| Time to first answer | 10.0 s | 6.5 s |
| Context window | 1M | 1.1M |
| Humanity's Last Exam | – | 44.3% |
| SimpleBench | – | 74.1% |
| SciCode | 48.6% | – |
| WeirdML | 68.8% | – |
| Epoch Capabilities Index | – | 158.9 |
| LMArena Text | 1462 | – |
| LMArena Hard Prompts | 1490 | – |
| LMArena Coding | 1521 | – |
| LMArena WebDev | 1538 | – |
| LMArena Vision | 1278 | – |
| LMArena Agent | 6.3 | – |
| AA Intelligence Index | 32.0 | – |
| AA-LCR | 76.7% | – |
| AA-Omniscience | -3.7 | – |
| Humanity's Last Exam (AA) | 35.7% | – |
| SciCode (AA) | 54.3% | – |
| MultiChallenge | – | 69.2% |
| VISTA | – | 53.9% |
| MultiNRC | – | 62.3% |
| TutorBench | – | 56.6% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5 vs GPT-5.4 Pro: questions
- Is Claude Sonnet 5 better than GPT-5.4 Pro?
- GPT-5.4 Pro leads on quality: 64.3 vs 61.4. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 Pro is ahead overall as of 2026-09-10, but check the category scores for your use.
- Which is cheaper, Claude Sonnet 5 or GPT-5.4 Pro?
- Claude Sonnet 5 is cheaper: $4.00 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Sonnet 5 or GPT-5.4 Pro?
- Claude Sonnet 5 streams faster: 60 against 1 output tokens per second.
- Which has the larger context window?
- GPT-5.4 Pro accepts more context: 1.1M against 1M tokens.