Claude Sonnet 5 vs GPT-5.2
Claude Sonnet 5 
GPT-5.2 Verdict
- Claude Sonnet 5 (high) and GPT-5.2 are level on quality (61.4 vs 61.6).
- Claude Sonnet 5 (high) is stronger in agents & tools, coding, composite, knowledge, multimodal, reasoning.
- GPT-5.2 is stronger in human preference, long context, instruction following.
- Claude Sonnet 5 (high) is 1.2× cheaper ($4.00 vs $4.81 per 1M blended).
| Metric | Claude Sonnet 5 (high) | GPT-5.2 |
|---|---|---|
| BenchLeader Index | 61.4 | 61.6 |
| Agents & tools score | 61.8 | 61.2 |
| Coding score | 61.6 | 53.7 |
| Composite score | 69.5 | 67.5 |
| Human preference score | 66.2 | 67.9 |
| Knowledge score | 62.4 | 61.1 |
| Long context score | 64.8 | 67.9 |
| Multimodal score | 63.1 | 59.9 |
| Reasoning score | 66.8 | 61.3 |
| Instruction following score | – | 67.4 |
| Blended price $/M | $4.00 | $4.81 |
| Output speed | 60 tok/s | 68 tok/s |
| Time to first answer | 10.0 s | 129.4 s |
| Context window | 1M | 400k |
| Humanity's Last Exam | – | 27.8% |
| Terminal-Bench | – | 64.9% |
| SimpleBench | – | 45.8% |
| SciCode | 48.6% | – |
| Remote Labor Index | – | 2.1% |
| WeirdML | 68.8% | – |
| APEX-Agents | – | 23.0% |
| Epoch Capabilities Index | – | 153.5 |
| LMArena Text | 1462 | 1476 |
| LMArena Hard Prompts | 1490 | 1497 |
| LMArena Coding | 1521 | 1515 |
| LMArena WebDev | 1538 | 1417 |
| LMArena Vision | 1278 | 1268 |
| LMArena Agent | 6.3 | – |
| AA Intelligence Index | 32.0 | 30.4 |
| IFBench | – | 75.4% |
| AA-LCR | 76.7% | 82.7% |
| AA-Omniscience | -3.7 | -0.9 |
| Terminal-Bench Hard | – | 47.0% |
| GPQA Diamond (AA) | – | 90.3% |
| Humanity's Last Exam (AA) | 35.7% | 37.7% |
| SciCode (AA) | 54.3% | – |
| τ²-Bench Telecom (AA) | – | 84.8% |
| SWE-Bench Pro | – | 29.9% |
| VISTA | – | 46.6% |
| MultiNRC | – | 42.2% |
| TutorBench | – | 53.5% |
| Kagi LLM Benchmark | – | 73.3% |
| SWE-bench Verified (bash only) | – | 69.0% |
| ARC-AGI-1 | – | 94.5% |
| ARC-AGI-2 | – | 72.9% |
| BFCL Overall | – | 55.9% |
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-5.2: questions
- Is Claude Sonnet 5 better than GPT-5.2?
- Claude Sonnet 5 (high) and GPT-5.2 are level on quality (61.4 vs 61.6). The BenchLeader Index combines every independent quality benchmark; GPT-5.2 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Sonnet 5 better than GPT-5.2 for coding?
- Claude Sonnet 5 scores higher in coding (62 vs 54 on the category index, where 50 is average).
- Is Claude Sonnet 5 better than GPT-5.2 for agentic tasks?
- Claude Sonnet 5 scores higher in agentic tasks (62 vs 61 on the category index, where 50 is average).
- Which is cheaper, Claude Sonnet 5 or GPT-5.2?
- Claude Sonnet 5 is cheaper: $4.00 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Sonnet 5 or GPT-5.2?
- GPT-5.2 streams faster: 68 against 60 output tokens per second.
- Which has the larger context window?
- Claude Sonnet 5 accepts more context: 1M against 400k tokens.