GPT-4o
Multimodal flagship released May 2024.
Benchmark results
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| Chatbot Arena | general | 1287 | yes | |
| HumanEval | coding | 90.2% | yes | |
| MATH | math | 76.6% | yes | |
| MMLU | reasoning | 88.7% | yes | |
| MMMU | multimodal | 69.1% | yes |
Multimodal flagship released May 2024.
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| Chatbot Arena | general | 1287 | yes | |
| HumanEval | coding | 90.2% | yes | |
| MATH | math | 76.6% | yes | |
| MMLU | reasoning | 88.7% | yes | |
| MMMU | multimodal | 69.1% | yes |