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 #69 across 526
Rank #89 across 436
Rank #159 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 | 41.2 | #69 |
| Artificial Analysis Coding Index | coding | 35.3 | #89 |
| Artificial Analysis Math Index | math | 90.7 | #23 |
| MMLU-Pro | reasoning | 83.7% | #50 |
| reasoning |
| 82.8% |
| #90 |
| Humanity's Last Exam | reasoning | 19.7% | #82 |
| LiveCodeBench | coding | 83.8% | #18 |
| SciCode | coding, reasoning | 39.2% | #128 |
| Output Speed | speed | 87.4 tok/s | #153 |
| Time to First Token | speed | 78.72s | #297 |
| Blended Price | cost | $0.688/M | #159 |
| Input Price | cost | $0.250/M | #126 |
| Output Price | cost | $2.00/M | #178 |
| Value Index | cost, overall | 59.9 | #107 |