SmolVLM-Synthetic: benchmark results
Provider: HuggingFace. Released 2024-11-26. Access: Open.
Aggregate Rating 1283 ± 28, rank #8948 of 10916 rated models, from 498 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Disaster Recognition | 100 | Score (%) | 96.8 |
| OpenVLM MMT-Bench - Order Hallucination | 60 | Score (%) | 96.6 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 45 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Gaze Estimation | 35 | Score (%) | 93 |
| OpenVLM MMT-Bench - Temporal Ordering | 40 | Score (%) | 92 |
| OpenVLM MMT-Bench - Social Relation Recognition | 65 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Texture Material Recognition | 80 | Score (%) | 84.5 |
| OpenVLM MMT-Bench - Scene Emotion Recognition | 60 | Score (%) | 80.6 |
| OpenVLM MMT-Bench - Spot The Diff | 70 | Score (%) | 80.3 |
| OpenVLM MMT-Bench - Attribute Hallucination | 80 | Score (%) | 78.6 |
| OpenVLM MMT-Bench - Rock Recognition | 65 | Score (%) | 76 |
| OpenVLM MMT-Bench - Table Structure Recognition | 75 | Score (%) | 74.5 |
Interactive version: theaggregate.ai/model?slug=smolvlm-synthetic · How It Works · Data refreshed daily, snapshot 2026-11-08.