Deepseek v4 Pro vs GPT-5.2
Deepseek v4 Pro 
GPT-5.2 Verdict
- Deepseek v4 Pro (high) and GPT-5.2 are level on quality (60.4 vs 60.3).
- Deepseek v4 Pro (high) is stronger in coding, maths, reasoning.
- GPT-5.2 is stronger in human preference, agents & tools, composite, instruction following, knowledge, long context, multimodal.
| Metric | Deepseek v4 Pro (high) | GPT-5.2 |
|---|---|---|
| BenchLeader Index | 60.4 | 60.3 |
| Coding score | 59.3 | 53.7 |
| Human preference score | 66.0 | 67.8 |
| Maths score | 66.2 | – |
| Reasoning score | 65.9 | 61.3 |
| Agents & tools score | – | 60.4 |
| Composite score | – | 61.6 |
| Instruction following score | – | 65.4 |
| Knowledge score | – | 58.8 |
| Long context score | – | 65.6 |
| Multimodal score | – | 59.9 |
| Blended price $/M | – | $4.81 |
| Output speed | – | 72 tok/s |
| Time to first answer | – | 90.8 s |
| Context window | – | 400k |
| GPQA Diamond | 90.9% | – |
| OTIS Mock AIME | 95.6% | – |
| Humanity's Last Exam | – | 27.8% |
| Terminal-Bench | – | 64.9% |
| SimpleBench | – | 45.8% |
| SciCode | 46.4% | – |
| Remote Labor Index | – | 2.1% |
| WeirdML | 46.5% | – |
| APEX-Agents | – | 23.0% |
| Epoch Capabilities Index | – | 153.5 |
| LMArena Text | 1462 | 1476 |
| LMArena Hard Prompts | 1482 | 1497 |
| LMArena Coding | 1505 | 1515 |
| LMArena WebDev | 1581 | 1417 |
| LMArena Vision | – | 1268 |
| AA Intelligence Index | – | 30.4 |
| IFBench | – | 75.4% |
| AA-LCR | – | 82.7% |
| AA-Omniscience | – | -0.9 |
| Terminal-Bench Hard | – | 47.0% |
| GPQA Diamond (AA) | – | 90.3% |
| Humanity's Last Exam (AA) | – | 37.7% |
| τ²-Bench Telecom (AA) | – | 84.8% |
| SWE-Bench Pro | – | 29.9% |
| VISTA | – | 46.6% |
| MultiNRC | – | 42.2% |
| TutorBench | – | 53.5% |
| Kagi LLM Benchmark | – | 73.3% |
| SWE-bench Verified (bash only) | – | 69.0% |
| ARC-AGI-1 | – | 94.5% |
| ARC-AGI-2 | – | 72.9% |
| BFCL Overall | – | 55.9% |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Deepseek v4 Pro vs GPT-5.2: questions
- Is Deepseek v4 Pro better than GPT-5.2?
- Deepseek v4 Pro (high) and GPT-5.2 are level on quality (60.4 vs 60.3). The BenchLeader Index combines every independent quality benchmark; Deepseek v4 Pro (high) is ahead overall as of 2026-09-13, but check the category scores for your use.
- Is Deepseek v4 Pro better than GPT-5.2 for coding?
- Deepseek v4 Pro scores higher in coding (59 vs 54 on the category index, where 50 is average).