Ovis1.6-Llama3.2-3B: benchmark results
Provider: Alibaba. Released 2024-10-22. Access: Open.
Aggregate Rating 1442 ± 34, rank #4121 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Depth Estimation | 90 | Score (%) | 100 |
| OpenVLM MMT-Bench - Existence Hallucination | 100 | Score (%) | 99 |
| OpenVLM MMT-Bench - Artwork Emotion Recognition | 65 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Disaster Recognition | 100 | Score (%) | 96.8 |
| OpenVLM MMT-Bench - PLP | 52.5 | Score (%) | 94.9 |
| OpenVLM MMT-Bench - Weather Recognition | 100 | Score (%) | 94.4 |
| OpenVLM MMT-Bench - Whoops | 95 | Score (%) | 94.2 |
| OpenVLM Q-Bench - Yes-or-No (Distortion) | 88.3 | Accuracy (%) | 94 |
| OpenVLM MMT-Bench - Shape Recognition | 95 | Score (%) | 93.7 |
| OpenVLM Q-Bench - What (Distortion) | 78.7 | Accuracy (%) | 93.4 |
| OpenVLM MMT-Bench - Pixel Localization | 45 | Score (%) | 93 |
| OpenVLM MMT-Bench - 3D | 55 | Score (%) | 90.8 |
Interactive version: theaggregate.ai/model?slug=ovis1-6-llama3-2-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.