GPT-4o (0806, detail-high): benchmark results
Provider: OpenAI. Released 2024-08-06. Access: API.
Aggregate Rating 1614 ± 28, rank #889 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MME - Posters | 193.5 | Score | 100 |
| OpenVLM MMT-Bench - Interactive Segmentation | 100 | Score (%) | 100 |
| OpenVLM MMT-Bench - Small Object Detection | 85 | Score (%) | 100 |
| OpenVLM MME - Count | 190 | Score | 99.8 |
| OpenVLM MME - Landmark | 189.2 | Score | 99.6 |
| OpenVLM SEEDBench IMG - Visual Reasoning | 84 | Accuracy (%) | 99.6 |
| OpenVLM MMT-Bench - Animated Character Recognition | 90 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Human Interaction Understanding | 95 | Score (%) | 99.3 |
| OpenVLM MMBench V1.1 EN - Action Recognition | 95.7 | Accuracy (%) | 99.1 |
| OpenVLM MME - OCR | 200 | Score | 99.1 |
| OpenVLM MMT-Bench - Building Recognition | 95 | Score (%) | 99 |
| OpenVLM MMT-Bench - Font Recognition | 55 | Score (%) | 99 |
Interactive version: theaggregate.ai/model?slug=gpt-4o-0806-detail-high · How It Works · Data refreshed daily, snapshot 2026-11-08.