OpenAI
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Introducing o3 and o4-miniRank #167 across 566
No rank
Rank #233 across 371
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 | 25.6 | #167 |
| Artificial Analysis Math Index | math | 90.7 | #23 |
| MMLU-Pro | reasoning | 83.2% | #61 |
| GPQA | reasoning | 78.4% | #161 |
| Humanity's Last Exam |
| reasoning |
| 17.5% |
| #123 |
| LiveCodeBench | coding | 85.9% | #12 |
| SciCode | coding, reasoning | 46.5% | #64 |
| MATH-500 | math | 98.9% | #7 |
| AIME | math | 94.0% | #3 |
| Output Speed | speed | 162.3 tok/s | #62 |
| Time to First Token | speed | 20.27s | #285 |
| Blended Price | cost | $1.93/M | #233 |
| Input Price | cost | $1.10/M | #237 |
| Output Price | cost | $4.40/M | #233 |
| Value Index | cost, overall | 13.3 | #212 |