Claude Sonnet 4.6 vs GPT-5.4 Pro
Claude Sonnet 4.6 
GPT-5.4 Pro Verdict
- GPT-5.4 Pro leads on quality: 64.3 vs 59.1.
- Claude Sonnet 4.6 is stronger in agents & tools, coding, composite, human preference, long context, maths.
- GPT-5.4 Pro is stronger in instruction following, knowledge, multimodal, reasoning.
- Claude Sonnet 4.6 is 11× cheaper ($6.00 vs $67.50 per 1M blended).
- Claude Sonnet 4.6 streams 42.8× faster (43 vs 1 tokens per second).
| Metric | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| BenchLeader Index | 59.1 | 64.3 |
| Agents & tools score | 53.7 | – |
| Coding score | 57.0 | – |
| Composite score | 61.6 | – |
| Human preference score | 62.0 | – |
| Instruction following score | 53.7 | 67.3 |
| Knowledge score | 61.4 | 73.6 |
| Long context score | 64.1 | – |
| Maths score | 62.7 | – |
| Multimodal score | 59.6 | 69.8 |
| Reasoning score | 65.2 | 75.3 |
| Blended price $/M | $6.00 | $67.50 |
| Output speed | 43 tok/s | 1 tok/s |
| Time to first answer | 1.7 s | 6.3 s |
| Context window | 1M | 1.1M |
| GPQA Diamond | 87.4% | – |
| OTIS Mock AIME | 85.8% | – |
| SWE-bench Verified (Epoch) | 75.2% | – |
| Humanity's Last Exam | – | 44.3% |
| Terminal-Bench | 53.4% | – |
| SimpleBench | – | 74.1% |
| FrontierCode | 24.3% | – |
| Epoch Capabilities Index | 152.3 | 158.9 |
| LMArena Text | 1473 | – |
| LMArena Hard Prompts | 1504 | – |
| LMArena Coding | 1528 | – |
| LMArena WebDev | 1521 | – |
| LMArena Vision | 1282 | – |
| LMArena Agent | -1.3 | – |
| AA Intelligence Index | 30.4 | – |
| IFBench | 56.6% | – |
| AA-LCR | 80.0% | – |
| MMMU-Pro | 73.3% | – |
| AA-Omniscience | 12.2 | – |
| Terminal-Bench Hard | 53.0% | – |
| GPQA Diamond (AA) | 87.5% | – |
| Humanity's Last Exam (AA) | 33.6% | – |
| SciCode (AA) | 50.1% | – |
| τ²-Bench Telecom (AA) | 79.5% | – |
| AIME (Vals) | 92.3% | – |
| LiveCodeBench | 82.1% | – |
| MMLU-Pro | 87.3% | – |
| LegalBench | 82.1% | – |
| CorpFin | 65.3% | – |
| TaxEval | 77.1% | – |
| MedQA | 92.1% | – |
| Terminal-Bench 2.1 (Vals) | 57.3% | – |
| SWE-bench (Vals) | 77.4% | – |
| GPQA Diamond (Vals) | 85.6% | – |
| Vals Index | 50.6 | – |
| MCP Atlas | 69.5% | – |
| MultiChallenge | – | 69.2% |
| VISTA | – | 53.9% |
| MultiNRC | – | 62.3% |
| TutorBench | – | 56.6% |
| EQ-Bench 4 | 1207 | – |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 4.6 vs GPT-5.4 Pro: questions
- Is Claude Sonnet 4.6 better than GPT-5.4 Pro?
- GPT-5.4 Pro leads on quality: 64.3 vs 59.1. 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 Sonnet 4.6 or GPT-5.4 Pro?
- Claude Sonnet 4.6 is cheaper: $6.00 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Sonnet 4.6 or GPT-5.4 Pro?
- Claude Sonnet 4.6 streams faster: 43 against 1 output tokens per second.
- Which has the larger context window?
- GPT-5.4 Pro accepts more context: 1.1M against 1M tokens.