GPT-5.2-Codex vs GPT-5 Pro
GPT-5.2-Codex Verdict
- GPT-5.2-Codex and GPT-5 Pro are level on quality (60.8 vs 60.8).
- GPT-5.2-Codex is stronger in agents & tools, coding, composite, instruction following, long context.
- GPT-5 Pro is stronger in knowledge, multimodal, reasoning.
- GPT-5.2-Codex is 8.6× cheaper ($4.81 vs $41.25 per 1M blended).
| Metric | GPT-5.2-Codex | GPT-5 Pro |
|---|---|---|
| BenchLeader Index | 60.8 | 60.8 |
| Agents & tools score | 63.5 | – |
| Coding score | 55.7 | – |
| Composite score | 56.8 | – |
| Instruction following score | 75.1 | – |
| Knowledge score | 63.1 | 68.0 |
| Long context score | 67.8 | – |
| Multimodal score | 60.7 | 67.4 |
| Reasoning score | – | 57.6 |
| Blended price $/M | $4.81 | $41.25 |
| Output speed | 25 tok/s | – |
| Time to first answer | 6.7 s | – |
| Context window | 400k | 400k |
| Humanity's Last Exam | – | 31.6% |
| Terminal-Bench | 66.5% | – |
| SimpleBench | – | 61.6% |
| APEX-Agents | 27.6% | – |
| Epoch Capabilities Index | – | 150.3 |
| LMArena WebDev | 1339 | – |
| LiveBench | 74.0% | – |
| LiveBench Reasoning | 77.7% | – |
| LiveBench Coding | 83.6% | – |
| LiveBench Agentic Coding | 49.4% | – |
| LiveBench Mathematics | 88.8% | – |
| LiveBench Data Analysis | 78.2% | – |
| LiveBench Language | 73.7% | – |
| 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% | – |
| LiveCodeBench | 88.0% | – |
| SWE-Bench Pro | 41.0% | – |
| PRBench Finance | – | 51.1% |
| PRBench Legal | – | 49.9% |
| VISTA | – | 52.4% |
| MultiNRC | – | 65.2% |
| Kagi LLM Benchmark | – | 76.8% |
| SWE-bench Verified (bash only) | 72.8% | – |
| SWE-bench Verified (any scaffold) | 72.8% | – |
| ARC-AGI-1 | – | 70.2% |
| ARC-AGI-2 | – | 18.3% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
GPT-5.2-Codex vs GPT-5 Pro: questions
- Is GPT-5.2-Codex better than GPT-5 Pro?
- GPT-5.2-Codex and GPT-5 Pro are level on quality (60.8 vs 60.8). The BenchLeader Index combines every independent quality benchmark; GPT-5 Pro is ahead overall as of 2026-09-10, but check the category scores for your use.
- Which is cheaper, GPT-5.2-Codex or GPT-5 Pro?
- GPT-5.2-Codex is cheaper: $4.81 against $41.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 400k tokens of context.