Ovis2-1B: benchmark results
Provider: Alibaba. Released 2025-03-12. Access: Open.
Aggregate Rating 1373 ± 18, rank #7071 of 10916 rated models, from 539 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM OCRBench - Text Recognition | 96.33 | Correct Answers (%) | 99.1 |
| OpenVLM MMT-Bench - 3D | 62.5 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Color Contrast | 85 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - 3D CAD Recognition | 80 | Score (%) | 98.5 |
| OpenVLM MMT-Bench - Musical Instrument Recognition | 100 | Score (%) | 98.3 |
| OpenVLM OCRBench - Key Information Extraction | 93 | Correct Answers (%) | 96.5 |
| OpenVLM MMT-Bench - Animal Keypoint Detection | 50 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - Traffic Light Understanding | 100 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - Science | 58.3 | Score (%) | 96.1 |
| OpenVLM MMT-Bench - Chart VQA | 80 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Relation Hallucination | 85 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - 3D Indoor Recognition | 45 | Score (%) | 91.5 |
Interactive version: theaggregate.ai/model?slug=ovis2-1b · How It Works · Data refreshed daily, snapshot 2026-11-08.