GPT-5.2-Codex vs GPT-5.5 Pro
GPT-5.2-Codex Verdict
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 60.7.
- GPT-5.2-Codex (xhigh) is stronger in agents & tools, composite, instruction following, knowledge, long context, multimodal.
- GPT-5.5 Pro (xhigh) is stronger in reasoning, maths.
- GPT-5.2-Codex (xhigh) is 14× cheaper ($4.81 vs $67.50 per 1M blended).
- GPT-5.2-Codex (xhigh) streams 7.5× faster (30 vs 4 tokens per second).
| Metric | GPT-5.2-Codex (xhigh) | GPT-5.5 Pro (xhigh) |
|---|---|---|
| BenchLeader Index | 60.7 | 67.1 |
| Agents & tools score | 65.9 | – |
| Composite score | 65.1 | – |
| Instruction following score | 75.3 | – |
| Knowledge score | 63.2 | – |
| Long context score | 67.7 | – |
| Multimodal score | 60.7 | – |
| Reasoning score | 58.7 | 80.1 |
| Maths score | – | 74.5 |
| Blended price $/M | $4.81 | $67.50 |
| Output speed | 30 tok/s | 4 tok/s |
| Time to first answer | 3.4 s | 3.5 s |
| Context window | 400k | 1.1M |
| FrontierMath Tiers 1–3 | – | 87.7% |
| FrontierMath Tier 4 | – | 78.0% |
| AA Intelligence Index | 28.5 | – |
| IFBench | 77.6% | – |
| AA-LCR | 82.3% | – |
| MMMU-Pro | 76.3% | – |
| AA-Omniscience | -2.2 | – |
| Terminal-Bench Hard | 37.1% | – |
| GPQA Diamond (AA) | 89.9% | – |
| Humanity's Last Exam (AA) | 35.7% | – |
| τ²-Bench Telecom (AA) | 92.1% | – |
| ARC-AGI-1 | – | 95.0% |
| ARC-AGI-2 | – | 84.2% |
| CritPt | 8.7% | 30.6% |
| LMCA | – | 53.9% |
| DTBench | – | 96.0% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
GPT-5.2-Codex vs GPT-5.5 Pro: questions
- Is GPT-5.2-Codex better than GPT-5.5 Pro?
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 60.7. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 Pro (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, GPT-5.2-Codex or GPT-5.5 Pro?
- GPT-5.2-Codex is cheaper: $4.81 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2-Codex or GPT-5.5 Pro?
- GPT-5.2-Codex streams faster: 30 against 4 output tokens per second.
- Which has the larger context window?
- GPT-5.5 Pro accepts more context: 1.1M against 400k tokens.