OpenAI
GPT-4o from OpenAI has broad general knowledge and domain expertise allowing it to follow complex instructions in natural language and solve difficult problems accurately. It matches GPT-4 Turbo performance with a faster and cheaper API.
OpenAI model releasesRank #277 across 523
Rank #243 across 433
Rank #301 across 355
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 | 18.6 | #277 |
| Artificial Analysis Coding Index | coding | 16.6 | #243 |
| GPQA | reasoning | 52.1% | #344 |
| Humanity's Last Exam | reasoning | 2.9% | #491 |
| LiveCodeBench |
| coding |
| 31.7% |
| #213 |
| SciCode | coding, reasoning | 33.1% | #234 |
| MATH-500 | math | 79.5% | #110 |
| AIME | math | 11.7% | #122 |
| Output Speed | speed | 94.1 tok/s | #139 |
| Time to First Token | speed | 0.55s | #56 |
| Blended Price | cost | $4.38/M | #301 |
| Input Price | cost | $2.50/M | #306 |
| Output Price | cost | $10.00/M | #289 |
| Value Index | cost, overall | 4.3 | #323 |