OpenAI
GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal balance between speed, cost, and capability.
Introducing GPT-5Rank #82 across 526
Rank #112 across 436
Rank #160 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 38.9 | #82 |
| Artificial Analysis Coding Index | coding | 32.8 | #112 |
| Artificial Analysis Math Index | math | 85.0 | #47 |
| MMLU-Pro | reasoning | 82.8% | #63 |
| reasoning |
| 80.3% |
| #114 |
| Humanity's Last Exam | reasoning | 14.6% | #114 |
| LiveCodeBench | coding | 69.2% | #77 |
| SciCode | coding, reasoning | 41.0% | #90 |
| Output Speed | speed | 86.7 tok/s | #157 |
| Time to First Token | speed | 13.95s | #269 |
| Blended Price | cost | $0.688/M | #160 |
| Input Price | cost | $0.250/M | #127 |
| Output Price | cost | $2.00/M | #179 |
| Value Index | cost, overall | 56.5 | #115 |