Ovis1.6-Gemma2-9B: benchmark results
Provider: Alibaba. Released 2024-09-19. Access: Open.
Aggregate Rating 1490 ± 25, rank #2508 of 10916 rated models, from 461 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMMU - Music | 56.7 | Accuracy (%) | 100 |
| OpenVLM MMT-Bench - Celebrity Recognition | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Color Contrast | 85 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Depth Estimation | 85 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Handwritten Text Recognition | 100 | Score (%) | 96.6 |
| OpenVLM MMT-Bench - Vehicle Retrieval | 90 | Score (%) | 96.6 |
| OpenVLM MMT-Bench - Polygon Localization | 70 | Score (%) | 96.1 |
| OpenVLM MMT-Bench - Face Detection | 85 | Score (%) | 95.9 |
| OpenVLM MMT-Bench - PLP | 53.3 | Score (%) | 95.9 |
| OpenVLM OCR-VQA | 71.2 | Accuracy (%) | 95.3 |
| OpenVLM Q-Bench - How (Distortion) | 66.5 | Accuracy (%) | 95.3 |
| OpenVLM MMT-Bench - Equation-to-LaTeX | 95 | Score (%) | 95.1 |
Interactive version: theaggregate.ai/model?slug=ovis1-6-gemma2-9b · How It Works · Data refreshed daily, snapshot 2026-11-08.