GPT-4v (1106, detail-high): benchmark results
Provider: OpenAI. Released 2023-11-06. Access: API.
Aggregate Rating 1487 ± 36, rank #2552 of 10916 rated models, from 199 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM SEEDBench IMG - Instance Interaction | 81.4 | Accuracy (%) | 98.4 |
| OpenVLM MMMU - Art and Design | 72.5 | Accuracy (%) | 94.3 |
| OpenVLM MMMU - Art | 80 | Accuracy (%) | 92.8 |
| OpenVLM MMMU - Sociology | 73.3 | Accuracy (%) | 91.3 |
| OpenVLM MMMU - Music | 43.3 | Accuracy (%) | 91.2 |
| OpenVLM MMMU - Economics | 76.7 | Accuracy (%) | 90.6 |
| OpenVLM MMMU - Basic Medical Science | 73.3 | Accuracy (%) | 90.1 |
| OpenVLM MMMU - Art Theory | 90 | Accuracy (%) | 89.9 |
| OpenVLM MMMU - Agriculture | 60 | Accuracy (%) | 85.3 |
| OpenVLM MMMU - Health and Medicine | 66 | Accuracy (%) | 84.6 |
| OpenVLM MMMU - Physics | 60 | Accuracy (%) | 83.9 |
| OpenVLM MMMU - Pharmacy | 73.3 | Accuracy (%) | 83.7 |
Interactive version: theaggregate.ai/model?slug=gpt-4v-1106-detail-high · How It Works · Data refreshed daily, snapshot 2026-11-08.