Ovis1.6-Gemma2-27B: benchmark results
Provider: Alibaba. Released 2024-11-26. Access: Open.
Aggregate Rating 1535 ± 19, rank #1898 of 10916 rated models, from 538 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Count | 66.6 | Score (%) | 100 |
| OpenVLM MMT-Bench - Counting By Category | 51.2 | Score (%) | 100 |
| OpenVLM MMT-Bench - RR | 85 | Score (%) | 100 |
| OpenVLM MMT-Bench - Counting By Visual Prompting | 60 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Spot The Similarity | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Traffic Participants Understanding | 75 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Body Emotion Recognition | 70 | Score (%) | 99 |
| OpenVLM MMT-Bench - Gaze Estimation | 40 | Score (%) | 99 |
| OpenVLM MMT-Bench - Vehicle Keypoint Detection | 100 | Score (%) | 98.5 |
| OpenVLM Q-Bench - Yes-or-No (In-context Others) | 92.9 | Accuracy (%) | 98.4 |
| OpenVLM MMT-Bench - Industrial Produce Anomaly Detection | 90 | Score (%) | 98.3 |
| OpenVLM OCR-VQA | 75.1 | Accuracy (%) | 98.3 |
Interactive version: theaggregate.ai/model?slug=ovis1-6-gemma2-27b · How It Works · Data refreshed daily, snapshot 2026-11-08.