GPT-5.2-Codex vs GPT-5.3-Codex
GPT-5.2-Codex Verdict
- GPT-5.3-Codex leads on quality: 62.5 vs 60.8.
- GPT-5.2-Codex is stronger in agents & tools, coding, instruction following.
- GPT-5.3-Codex is stronger in composite, knowledge, long context, multimodal.
- They cost about the same ($4.81 per 1M blended).
- GPT-5.3-Codex streams 4.8× faster (121 vs 25 tokens per second).
| Metric | GPT-5.2-Codex | GPT-5.3-Codex |
|---|---|---|
| BenchLeader Index | 60.8 | 62.5 |
| Agents & tools score | 63.5 | 62.7 |
| Coding score | 55.7 | 54.8 |
| Composite score | 56.8 | 70.1 |
| Instruction following score | 75.1 | 73.2 |
| Knowledge score | 63.1 | 69.3 |
| Long context score | 67.8 | 68.3 |
| Multimodal score | 60.7 | 63.0 |
| Blended price $/M | $4.81 | $4.81 |
| Output speed | 25 tok/s | 121 tok/s |
| Time to first answer | 6.7 s | 58.2 s |
| Context window | 400k | 400k |
| Terminal-Bench | 66.5% | 78.4% |
| WeirdML | – | 79.3% |
| APEX-Agents | 27.6% | 31.8% |
| Epoch Capabilities Index | – | 156.6 |
| LMArena WebDev | 1339 | 1409 |
| 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 | 32.5 |
| IFBench | 77.6% | 75.4% |
| AA-LCR | 82.3% | 83.3% |
| MMMU-Pro | 76.3% | 78.5% |
| AA-Omniscience | -2.2 | 10.9 |
| Terminal-Bench Hard | 37.1% | 53.0% |
| GPQA Diamond (AA) | 89.9% | 91.5% |
| Humanity's Last Exam (AA) | 35.7% | 42.5% |
| τ²-Bench Telecom (AA) | 92.1% | 86.0% |
| LiveCodeBench | 88.0% | – |
| SWE-Bench Pro | 41.0% | – |
| HiL-Bench | – | 4.3% |
| SWE-bench Verified (bash only) | 72.8% | – |
| SWE-bench Verified (any scaffold) | 72.8% | – |
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-5.3-Codex: questions
- Is GPT-5.2-Codex better than GPT-5.3-Codex?
- GPT-5.3-Codex leads on quality: 62.5 vs 60.8. The BenchLeader Index combines every independent quality benchmark; GPT-5.3-Codex is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is GPT-5.2-Codex better than GPT-5.3-Codex for coding?
- GPT-5.2-Codex scores higher in coding (56 vs 55 on the category index, where 50 is average).
- Is GPT-5.2-Codex better than GPT-5.3-Codex for agentic tasks?
- GPT-5.2-Codex scores higher in agentic tasks (64 vs 63 on the category index, where 50 is average).
- Which is cheaper, GPT-5.2-Codex or GPT-5.3-Codex?
- GPT-5.2-Codex is cheaper: $4.81 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2-Codex or GPT-5.3-Codex?
- GPT-5.3-Codex streams faster: 121 against 25 output tokens per second.
- Which has the larger context window?
- Both accept 400k tokens of context.