OpenAI
GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal (accepting text or image inputs and outputting text) and has higher intelligence than gpt-3.5-turbo but is just as fast.
OpenAI model releasesRank #382 across 526
No rank
Rank #89 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 | 12.6 | #382 |
| Artificial Analysis Math Index | math | 14.7 | #219 |
| MMLU-Pro | reasoning | 64.8% | #253 |
| GPQA | reasoning | 42.6% | #401 |
| Humanity's Last Exam |
| reasoning |
| 4.0% |
| #432 |
| LiveCodeBench | coding | 23.4% | #258 |
| SciCode | coding, reasoning | 22.9% | #362 |
| MATH-500 | math | 78.9% | #112 |
| AIME | math | 11.7% | #123 |
| Output Speed | speed | 69.7 tok/s | #183 |
| Time to First Token | speed | 0.55s | #57 |
| Blended Price | cost | $0.262/M | #89 |
| Input Price | cost | $0.150/M | #83 |
| Output Price | cost | $0.600/M | #100 |
| Value Index | cost, overall | 48.1 | #127 |