SmolVLM-Instruct: benchmark results
Provider: HuggingFace. Released 2024-11-26. Access: Open.
Aggregate Rating 1335 ± 20, rank #8064 of 10916 rated models, from 552 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LMM Reasoning - WeMath - InsufficientKnowledge (Loose) | 68.8 | Accuracy (%) | 96.3 |
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 75 | Score (%) | 94.4 |
| OpenVLM MMT-Bench - Action Quality Assessment | 35 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Counting By Category | 42.5 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Industrial Produce Anomaly Detection | 85 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Spot The Diff | 85 | Score (%) | 92.7 |
| OpenVLM MMT-Bench - Attribute Hallucination | 85 | Score (%) | 92.5 |
| Open LMM Reasoning - WeMath - RoteMemorization (Strict) | 77.4 | Accuracy (%) | 91.4 |
| Open LMM Reasoning - WeMath - RoteMemorization (Loose) | 20.2 | Accuracy (%) | 89.5 |
| OpenVLM MMT-Bench - Disaster Recognition | 95 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - MIA | 67.5 | Score (%) | 85.7 |
Interactive version: theaggregate.ai/model?slug=smolvlm-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.