GPT-5.1 vs GPT-5.5
GPT-5.1 Verdict
- GPT-5.5 leads on quality: 66.7 vs 59.6.
- GPT-5.5 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, multimodal, reasoning.
- GPT-5.1 is 3.3× cheaper ($3.44 vs $11.25 per 1M blended).
| Metric | GPT-5.1 | GPT-5.5 |
|---|---|---|
| BenchLeader Index | 59.6 | 66.7 |
| Agents & tools score | 55.7 | 68.5 |
| Coding score | 47.1 | 57.2 |
| Composite score | 60.3 | 77.8 |
| Human preference score | 63.3 | 67.9 |
| Instruction following score | 71.0 | 73.6 |
| Knowledge score | 66.7 | 73.9 |
| Long context score | 66.6 | 68.8 |
| Multimodal score | 61.8 | 64.9 |
| Reasoning score | 58.7 | 70.1 |
| Blended price $/M | $3.44 | $11.25 |
| Output speed | 91 tok/s | 85 tok/s |
| Time to first answer | 43.1 s | 58.6 s |
| Context window | 400k | 1.1M |
| Humanity's Last Exam | 23.7% | – |
| Terminal-Bench | 47.6% | 84.7% |
| SimpleBench | – | 69.0% |
| SciCode | 43.3% | – |
| Remote Labor Index | – | 6.3% |
| APEX-Agents | 17.5% | 38.5% |
| FrontierCode | – | 43.0% |
| GSO-Bench | 13.7% | – |
| Epoch Capabilities Index | 149.7 | 159.1 |
| LMArena Text | 1439 | 1477 |
| LMArena Hard Prompts | 1456 | 1498 |
| LMArena Coding | 1475 | 1509 |
| LMArena WebDev | 1341 | 1458 |
| LMArena Vision | 1235 | 1296 |
| LMArena Agent | – | 3 |
| AA Intelligence Index | 24.7 | 38.6 |
| IFBench | 72.9% | 75.8% |
| AA-LCR | 80.0% | 84.3% |
| MMMU-Pro | 75.5% | 79.9% |
| AA-Omniscience | 5.4 | 20.5 |
| Terminal-Bench Hard | 45.5% | 60.6% |
| GPQA Diamond (AA) | 87.3% | 93.5% |
| Humanity's Last Exam (AA) | 28.5% | 45.8% |
| SciCode (AA) | – | 55.8% |
| τ²-Bench Telecom (AA) | 81.9% | 93.9% |
| HiL-Bench | – | 39.7% |
| EQ-Bench 4 | – | 1315 |
| MMMU (validation) | 85.4% | – |
| MMMU-Pro (official) | 76.0% | – |
| Kagi LLM Benchmark | – | 88.8% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
GPT-5.1 vs GPT-5.5: questions
- Is GPT-5.1 better than GPT-5.5?
- GPT-5.5 leads on quality: 66.7 vs 59.6. 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-5.1 better than GPT-5.5 for coding?
- GPT-5.5 scores higher in coding (57 vs 47 on the category index, where 50 is average).
- Is GPT-5.1 better than GPT-5.5 for agentic tasks?
- GPT-5.5 scores higher in agentic tasks (69 vs 56 on the category index, where 50 is average).
- Which is cheaper, GPT-5.1 or GPT-5.5?
- GPT-5.1 is cheaper: $3.44 against $11.25 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.1 or GPT-5.5?
- GPT-5.1 streams faster: 91 against 85 output tokens per second.
- Which has the larger context window?
- GPT-5.5 accepts more context: 1.1M against 400k tokens.