VARCO-VISION-2.0-1.7B: benchmark results
Provider: Samsung. Released 2025-02-10. Access: Open.
Aggregate Rating 1420 ± 19, rank #5182 of 10916 rated models, from 175 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMBench V1.1 CN - Identity Reasoning | 98.7 | Accuracy (%) | 86.6 |
| OpenVLM OCRBench - Handwritten Mathematical Expression Recognition | 74 | Correct Answers (%) | 82.6 |
| OpenVLM MMMU - Math | 53.3 | Accuracy (%) | 80.6 |
| OpenVLM MMBench V1.1 EN - Image Emotion | 80 | Accuracy (%) | 76 |
| OpenVLM MMBench V1.1 CN - Action Recognition | 88 | Accuracy (%) | 75.3 |
| OpenVLM MathVista - NUM | 44.4 | Accuracy (%) | 71.8 |
| OpenVLM MMMU - Mechanical Engineering | 43.3 | Accuracy (%) | 71.6 |
| OpenVLM MMBench V1.1 EN - Image Scene | 88.9 | Accuracy (%) | 71.4 |
| OpenVLM MMBench V1.1 EN - Identity Reasoning | 97.4 | Accuracy (%) | 71 |
| OpenVLM MMBench V1.1 EN - Social Relation | 86.8 | Accuracy (%) | 70.8 |
| OpenVLM MMBench V1.1 CN - Attribute Comparison | 76 | Accuracy (%) | 70.7 |
| OpenVLM MMMU - Chemistry | 50 | Accuracy (%) | 69.8 |
Interactive version: theaggregate.ai/model?slug=varco-vision-2-0-1-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.