OpenAI
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
OpenAI model releasesRank #368 across 566
Rank #198 across 222
Rank #50 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 | 9.6 | #368 |
| Artificial Analysis Coding Index | coding | 11.1 | #198 |
| Artificial Analysis Math Index | math | 24.0 | #201 |
| MMLU-Pro | reasoning | 65.7% | #256 |
| reasoning |
| 51.2% |
| #393 |
| Humanity's Last Exam | reasoning | 3.9% | #480 |
| LiveCodeBench | coding | 32.6% | #209 |
| SciCode | coding, reasoning | 25.9% | #367 |
| MATH-500 | math | 84.8% | #96 |
| AIME | math | 23.7% | #96 |
| Output Speed | speed | 148 tok/s | #75 |
| Time to First Token | speed | 0.44s | #22 |
| Blended Price | cost | $0.175/M | #50 |
| Input Price | cost | $0.100/M | #36 |
| Output Price | cost | $0.400/M | #55 |
| Value Index | cost, overall | 54.9 | #77 |