GPT-5.5 vs GPT-5-Codex
GPT-5.5 Verdict
- GPT-5.5 leads on quality: 66.7 vs 58.2.
- GPT-5.5 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, multimodal, reasoning.
- GPT-5-Codex is 3.3× cheaper ($3.44 vs $11.25 per 1M blended).
| Metric | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| BenchLeader Index | 66.7 | 58.2 |
| Agents & tools score | 68.5 | 56.3 |
| Coding score | 57.2 | 53.6 |
| Composite score | 77.8 | 60.4 |
| Human preference score | 67.9 | – |
| Instruction following score | 73.6 | 72.1 |
| Knowledge score | 73.9 | 60.6 |
| Long context score | 68.8 | 62.2 |
| Multimodal score | 64.9 | 58.2 |
| Reasoning score | 70.1 | 64.3 |
| Blended price $/M | $11.25 | $3.44 |
| Output speed | 85 tok/s | – |
| Time to first answer | 58.6 s | – |
| Context window | 1.1M | 400k |
| Terminal-Bench | 84.7% | 44.3% |
| SimpleBench | 69.0% | – |
| Remote Labor Index | 6.3% | – |
| WeirdML | – | 54.5% |
| APEX-Agents | 38.5% | – |
| FrontierCode | 43.0% | – |
| Epoch Capabilities Index | 159.1 | – |
| LMArena Text | 1477 | – |
| LMArena Hard Prompts | 1498 | – |
| LMArena Coding | 1509 | – |
| LMArena WebDev | 1458 | – |
| LMArena Vision | 1296 | – |
| LMArena Agent | 3 | – |
| AA Intelligence Index | 38.6 | 24.9 |
| IFBench | 75.8% | 74.2% |
| AA-LCR | 84.3% | 71.7% |
| MMMU-Pro | 79.9% | 73.8% |
| AA-Omniscience | 20.5 | -7.5 |
| Terminal-Bench Hard | 60.6% | 37.9% |
| GPQA Diamond (AA) | 93.5% | 83.7% |
| Humanity's Last Exam (AA) | 45.8% | 27.9% |
| SciCode (AA) | 55.8% | – |
| τ²-Bench Telecom (AA) | 93.9% | 86.8% |
| HiL-Bench | 39.7% | – |
| EQ-Bench 4 | 1315 | – |
| Kagi LLM Benchmark | 88.8% | 70.3% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
GPT-5.5 vs GPT-5-Codex: questions
- Is GPT-5.5 better than GPT-5-Codex?
- GPT-5.5 leads on quality: 66.7 vs 58.2. 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-5.5 better than GPT-5-Codex for coding?
- GPT-5.5 scores higher in coding (57 vs 54 on the category index, where 50 is average).
- Is GPT-5.5 better than GPT-5-Codex 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-5.5 or GPT-5-Codex?
- GPT-5-Codex is cheaper: $3.44 against $11.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- GPT-5.5 accepts more context: 1.1M against 400k tokens.