| Benchmark | Model | Rank | Results |
|---|---|---|---|
| chart-question-answering-on-chartqa | GPT-4o | – | 1:1 Accuracy: 85.7 |
| code-generation-on-humaneval | GPT-4o | – | Pass@1: 90.2 |
| math-word-problem-solving-on-math | GPT-4o | – | Accuracy: 76.6 |
| math-word-problem-solving-on-mgsm-0-shot | GPT-4o | – | Accuracy: 90.5 |
| multimodal-reasoning-on-mathvista | GPT-4o | – | Accuracy: 63.8 |
| multimodal-reasoning-on-mmmu | GPT-4o | – | Accuracy: 69.1 |
| visual-question-answering-on-docvqa-test | GPT-4o | – | ANLS: 0.928 |
| zero-shot-video-question-answer-on-egoschema-fullset | GPT-4o | – | Accuracy: 72.2 |