Ovis2-2B: benchmark results
Provider: Alibaba. Released 2025-03-12. Access: Open.
Aggregate Rating 1448 ± 15, rank #3869 of 10916 rated models, from 548 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Facial Expression Change Recognition | 100 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Meme Image Understanding | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Traffic Participants Understanding | 75 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Existence Hallucination | 100 | Score (%) | 99 |
| OpenVLM MMT-Bench - Industrial Produce Anomaly Detection | 90 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - Depth Estimation | 85 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Pixel Localization | 55 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Body Emotion Recognition | 65 | Score (%) | 96.8 |
| OpenVLM MMT-Bench - MeViS | 50 | Score (%) | 96.1 |
| OpenVLM MMT-Bench - TU | 51.5 | Score (%) | 95.6 |
| OpenVLM MMT-Bench - Texture Material Recognition | 85 | Score (%) | 95.4 |
| OpenVLM MMT-Bench - PLP | 52.5 | Score (%) | 94.9 |
Interactive version: theaggregate.ai/model?slug=ovis2-2b · How It Works · Data refreshed daily, snapshot 2026-11-08.