GPT-5.2 vs GPT-5.4
GPT-5.2 Verdict
- GPT-5.4 leads on quality: 63.5 vs 61.6.
- GPT-5.2 is stronger in coding, human preference, long context.
- GPT-5.4 is stronger in agents & tools, composite, instruction following, knowledge, multimodal, reasoning.
- GPT-5.2 is 1.2× cheaper ($4.81 vs $5.63 per 1M blended).
- GPT-5.4 streams 1.9× faster (129 vs 68 tokens per second).
| Metric | GPT-5.2 | GPT-5.4 |
|---|---|---|
| BenchLeader Index | 61.6 | 63.5 |
| Agents & tools score | 61.2 | 66.2 |
| Coding score | 53.7 | 51.6 |
| Composite score | 67.5 | 78.3 |
| Human preference score | 67.9 | 64.7 |
| Instruction following score | 67.4 | 71.9 |
| Knowledge score | 61.1 | 66.9 |
| Long context score | 67.9 | 67.6 |
| Multimodal score | 59.9 | 64.0 |
| Reasoning score | 61.3 | 62.6 |
| Blended price $/M | $4.81 | $5.63 |
| Output speed | 68 tok/s | 129 tok/s |
| Time to first answer | 129.4 s | 124.6 s |
| Context window | 400k | 1.1M |
| Humanity's Last Exam | 27.8% | – |
| Terminal-Bench | 64.9% | 81.8% |
| SimpleBench | 45.8% | – |
| Remote Labor Index | 2.1% | – |
| APEX-Agents | 23.0% | 34.9% |
| Epoch Capabilities Index | 153.5 | 156.9 |
| LMArena Text | 1476 | 1466 |
| LMArena Hard Prompts | 1497 | 1488 |
| LMArena Coding | 1515 | 1514 |
| LMArena WebDev | 1417 | 1386 |
| LMArena Vision | 1268 | 1293 |
| AA Intelligence Index | 30.4 | 39.0 |
| IFBench | 75.4% | 74.0% |
| AA-LCR | 82.7% | 82.0% |
| MMMU-Pro | – | 78.4% |
| AA-Omniscience | -0.9 | 5.8 |
| Terminal-Bench Hard | 47.0% | 57.6% |
| GPQA Diamond (AA) | 90.3% | 92.0% |
| Humanity's Last Exam (AA) | 37.7% | 43.7% |
| τ²-Bench Telecom (AA) | 84.8% | 87.1% |
| SWE-Bench Pro | 29.9% | – |
| VISTA | 46.6% | – |
| MultiNRC | 42.2% | – |
| HiL-Bench | – | 9.7% |
| TutorBench | 53.5% | – |
| EQ-Bench 4 | – | 1272 |
| Kagi LLM Benchmark | 73.3% | 63.8% |
| SWE-bench Verified (bash only) | 69.0% | – |
| ARC-AGI-1 | 94.5% | – |
| ARC-AGI-2 | 72.9% | – |
| BFCL Overall | 55.9% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
GPT-5.2 vs GPT-5.4: questions
- Is GPT-5.2 better than GPT-5.4?
- GPT-5.4 leads on quality: 63.5 vs 61.6. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is GPT-5.2 better than GPT-5.4 for coding?
- GPT-5.2 scores higher in coding (54 vs 52 on the category index, where 50 is average).
- Is GPT-5.2 better than GPT-5.4 for agentic tasks?
- GPT-5.4 scores higher in agentic tasks (66 vs 61 on the category index, where 50 is average).
- Which is cheaper, GPT-5.2 or GPT-5.4?
- GPT-5.2 is cheaper: $4.81 against $5.63 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2 or GPT-5.4?
- GPT-5.4 streams faster: 129 against 68 output tokens per second.
- Which has the larger context window?
- GPT-5.4 accepts more context: 1.1M against 400k tokens.