Chameleon-30B: benchmark results
Provider: Meta. Released 2024-06-16. Access: Open.
Aggregate Rating 1256 ± 47, rank #9035 of 10489 rated models, from 418 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Animated Character Recognition | 50 | Score (%) | 66.3 |
| OpenVLM MMMU - Mechanical Engineering | 40 | Accuracy (%) | 64 |
| OpenVLM MMT-Bench - Jigsaw Puzzle Solving | 30 | Score (%) | 63.3 |
| OpenVLM MMT-Bench - Tech Engineering | 33.3 | Score (%) | 62.4 |
| OpenVLM MMT-Bench - Sign Language Recognition | 35 | Score (%) | 60.9 |
| OpenVLM MMT-Bench - Spot The Diff | 30 | Score (%) | 58.7 |
| OpenVLM MMT-Bench - Animals Recognition | 90 | Score (%) | 58 |
| OpenVLM MMT-Bench - Interactive Segmentation | 42.9 | Score (%) | 57.3 |
| OpenVLM MMT-Bench - Gaze Estimation | 20 | Score (%) | 56.8 |
| OpenVLM MMMU - History | 63.3 | Accuracy (%) | 55.1 |
| OpenVLM MMMU - Chemistry | 43.3 | Accuracy (%) | 54.6 |
| OpenVLM MMT-Bench - Navigation | 55 | Score (%) | 54.4 |
Interactive version: theaggregate.ai/model?slug=chameleon-30b · How It Works · Data refreshed daily, snapshot 2026-11-20.