SmolVLM-256M: benchmark results
Provider: HuggingFace. Released 2025-01-23. Access: Open.
Aggregate Rating 1172 ± 38, rank #9762 of 10916 rated models, from 502 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Animal Keypoint Detection | 55 | Score (%) | 99 |
| OpenVLM MMT-Bench - Temporal Ordering | 45 | Score (%) | 97.6 |
| OpenVLM MMT-Bench - Image Matting | 35 | Score (%) | 95.6 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 45 | Score (%) | 94.2 |
| Open LMM Reasoning - MathVision - topology | 30.4 | Accuracy (%) | 89.3 |
| OpenVLM MMT-Bench - Rotated Object Detection | 66.7 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Small Object Detection | 55 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Writing Poetry From Image | 60 | Score (%) | 83.5 |
| OpenVLM MMT-Bench - Color Assimilation | 65 | Score (%) | 75 |
| OpenVLM MMT-Bench - Table Structure Recognition | 75 | Score (%) | 74.5 |
| OpenVLM MMT-Bench - Google Apps | 40 | Score (%) | 74 |
| OpenVLM MMMU - Geography | 53.3 | Accuracy (%) | 68.9 |
Interactive version: theaggregate.ai/model?slug=smolvlm-256m · How It Works · Data refreshed daily, snapshot 2026-11-08.