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 #283 across 526
Rank #242 across 436
Rank #303 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 | 17.3 | #283 |
| Artificial Analysis Coding Index | coding | 16.7 | #242 |
| Artificial Analysis Math Index | math | 6.0 | #245 |
| MMLU-Pro | reasoning | 74.8% | #181 |
| reasoning |
| 54.3% |
| #333 |
| Humanity's Last Exam | reasoning | 3.3% | #488 |
| LiveCodeBench | coding | 30.9% | #217 |
| SciCode | coding, reasoning | 33.3% | #229 |
| MATH-500 | math | 75.9% | #125 |
| AIME | math | 15.0% | #112 |
| Output Speed | speed | 142.1 tok/s | #87 |
| Time to First Token | speed | 0.61s | #72 |
| Blended Price | cost | $4.38/M | #303 |
| Input Price | cost | $2.50/M | #308 |
| Output Price | cost | $10.00/M | #291 |
| Value Index | cost, overall | 4.0 | #324 |