Emu2_chat: benchmark results
Provider: BAAI. Released 2023-12-22. Access: Open.
Aggregate Rating 1261 ± 45, rank #9156 of 10916 rated models, from 212 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM COCO Captions | 109.2 | CIDEr | 100 |
| OpenVLM MMMU - Agriculture | 60 | Accuracy (%) | 85.3 |
| OpenVLM MMMU - Diagnostics and Laboratory Medicine | 46.7 | Accuracy (%) | 82.3 |
| OpenVLM POPE | 88 | Overall (%) | 80.9 |
| OpenVLM SEEDBench IMG - Text Understanding | 69 | Accuracy (%) | 79.3 |
| OpenVLM MME - Celebrity | 156.8 | Score | 76.9 |
| OpenVLM MMBench V1.1 EN - Identity Reasoning | 97.4 | Accuracy (%) | 71 |
| OpenVLM LLaVA-Bench - Conv | 82.2 | Score | 70.6 |
| OpenVLM MMBench V1.1 EN - Action Recognition | 88 | Accuracy (%) | 69.3 |
| OpenVLM MMMU - Mechanical Engineering | 40 | Accuracy (%) | 64 |
| OpenVLM MME - Existence | 195 | Score | 63.5 |
| OpenVLM MMBench V1.1 EN - Image Topic | 97.8 | Accuracy (%) | 62.4 |
Interactive version: theaggregate.ai/model?slug=emu2-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.