OpenAI
GPT-5.2 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.
Introducing GPT-5Rank #33 across 526
Rank #36 across 436
Rank #307 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 46.6 | #33 |
| Artificial Analysis Coding Index | coding | 44.2 | #36 |
| Artificial Analysis Math Index | math | 96.7 | #5 |
| MMLU-Pro | reasoning | 85.9% | #24 |
| reasoning |
| 86.4% |
| #49 |
| Humanity's Last Exam | reasoning | 24.9% | #58 |
| LiveCodeBench | coding | 89.4% | #5 |
| SciCode | coding, reasoning | 46.2% | #44 |
| Blended Price | cost | $4.81/M | #307 |
| Input Price | cost | $1.75/M | #285 |
| Output Price | cost | $14.00/M | #309 |
| Value Index | cost, overall | 9.7 | #276 |