OpenAI
GPT-4o (March 2025, chatgpt-4o-latest) is a OpenAI language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.
OpenAI model releasesQueryable facts extracted from the upstream model payload.
Rank #196 across 269 models.
Percentile score by analysis domain.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 18.6 | #258 |
| Artificial Analysis Math Index | math | 25.7 | #196 |
| MMLU-Pro | reasoning | 80.3% | #111 |
| GPQA | reasoning | 65.5% | #244 |
| Humanity's Last Exam |
| reasoning |
| 5.0% |
| #298 |
| LiveCodeBench | coding | 42.5% | #170 |
| SciCode | coding, reasoning | 36.6% | #160 |
| MATH-500 | math | 89.3% | #75 |
| AIME | math | 32.7% | #78 |