SmolVLM-Instruct-DPO: benchmark results
Provider: HuggingFace. Released 2024-11-26. Access: Open.
Aggregate Rating 1309 ± 25, rank #8560 of 10916 rated models, from 498 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Counting By Category | 43.8 | Score (%) | 95.9 |
| OpenVLM MMT-Bench - Micro Expression Recognition | 45 | Score (%) | 94.9 |
| OpenVLM MMT-Bench - Whoops | 95 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Industrial Produce Anomaly Detection | 85 | Score (%) | 93.7 |
| OpenVLM MME - Scene | 166.2 | Score | 92.9 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 40 | Score (%) | 89.3 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 70 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Chemical Apparatus Recognition | 70 | Score (%) | 86.9 |
| OpenVLM MMT-Bench - Gaze Estimation | 30 | Score (%) | 83.7 |
| OpenVLM MMT-Bench - Spot The Diff | 75 | Score (%) | 83.5 |
| OpenVLM MMT-Bench - Animal Keypoint Detection | 40 | Score (%) | 82 |
| OpenVLM MMT-Bench - Traffic Participants Understanding | 60 | Score (%) | 81.6 |
Interactive version: theaggregate.ai/model?slug=smolvlm-instruct-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.