GPT-5.2 vs GPT-5.5
GPT-5.2 Verdict
- GPT-5.5 leads on quality: 66.7 vs 61.6.
- GPT-5.5 is stronger in agents & tools, coding, composite, instruction following, knowledge, long context, multimodal, reasoning.
- GPT-5.2 is 2.3× cheaper ($4.81 vs $11.25 per 1M blended).
| Metric | GPT-5.2 | GPT-5.5 |
|---|---|---|
| BenchLeader Index | 61.6 | 66.7 |
| Agents & tools score | 61.2 | 68.5 |
| Coding score | 53.7 | 57.2 |
| Composite score | 67.5 | 77.8 |
| Human preference score | 67.9 | 67.9 |
| Instruction following score | 67.4 | 73.6 |
| Knowledge score | 61.1 | 73.9 |
| Long context score | 67.9 | 68.8 |
| Multimodal score | 59.9 | 64.9 |
| Reasoning score | 61.3 | 70.1 |
| Blended price $/M | $4.81 | $11.25 |
| Output speed | 68 tok/s | 85 tok/s |
| Time to first answer | 129.4 s | 58.6 s |
| Context window | 400k | 1.1M |
| Humanity's Last Exam | 27.8% | – |
| Terminal-Bench | 64.9% | 84.7% |
| SimpleBench | 45.8% | 69.0% |
| Remote Labor Index | 2.1% | 6.3% |
| APEX-Agents | 23.0% | 38.5% |
| FrontierCode | – | 43.0% |
| Epoch Capabilities Index | 153.5 | 159.1 |
| LMArena Text | 1476 | 1477 |
| LMArena Hard Prompts | 1497 | 1498 |
| LMArena Coding | 1515 | 1509 |
| LMArena WebDev | 1417 | 1458 |
| LMArena Vision | 1268 | 1296 |
| LMArena Agent | – | 3 |
| AA Intelligence Index | 30.4 | 38.6 |
| IFBench | 75.4% | 75.8% |
| AA-LCR | 82.7% | 84.3% |
| MMMU-Pro | – | 79.9% |
| AA-Omniscience | -0.9 | 20.5 |
| Terminal-Bench Hard | 47.0% | 60.6% |
| GPQA Diamond (AA) | 90.3% | 93.5% |
| Humanity's Last Exam (AA) | 37.7% | 45.8% |
| SciCode (AA) | – | 55.8% |
| τ²-Bench Telecom (AA) | 84.8% | 93.9% |
| SWE-Bench Pro | 29.9% | – |
| VISTA | 46.6% | – |
| MultiNRC | 42.2% | – |
| HiL-Bench | – | 39.7% |
| TutorBench | 53.5% | – |
| EQ-Bench 4 | – | 1315 |
| Kagi LLM Benchmark | 73.3% | 88.8% |
| 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.
GPT-5.2 vs GPT-5.5: questions
- Is GPT-5.2 better than GPT-5.5?
- GPT-5.5 leads on quality: 66.7 vs 61.6. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is GPT-5.2 better than GPT-5.5 for coding?
- GPT-5.5 scores higher in coding (57 vs 54 on the category index, where 50 is average).
- Is GPT-5.2 better than GPT-5.5 for agentic tasks?
- GPT-5.5 scores higher in agentic tasks (69 vs 61 on the category index, where 50 is average).
- Which is cheaper, GPT-5.2 or GPT-5.5?
- GPT-5.2 is cheaper: $4.81 against $11.25 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2 or GPT-5.5?
- GPT-5.5 streams faster: 85 against 68 output tokens per second.
- Which has the larger context window?
- GPT-5.5 accepts more context: 1.1M against 400k tokens.