VARCO-VISION-14B: benchmark results
Provider: Samsung. Released 2024-11-19. Access: Open.
Aggregate Rating 1531 ± 17, rank #1937 of 10916 rated models, from 503 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - PLP | 55 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Tech Engineering | 66.7 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - LVLM Response Judgement | 70 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Polygon Localization | 75 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Social Relation Recognition | 80 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Temporal Sequence Understanding | 60 | Score (%) | 98.8 |
| OpenVLM MME - Position | 175 | Score | 98.7 |
| OpenVLM COCO Captions | 95.1 | CIDEr | 98.6 |
| OpenVLM Q-Bench - Yes-or-No (In-context Others) | 92.9 | Accuracy (%) | 98.4 |
| OpenVLM MMT-Bench - IEJ | 65 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - Image Season Recognition | 90 | Score (%) | 98.3 |
| OpenVLM MMBench V1.1 EN - Attribute Comparison | 92 | Accuracy (%) | 98.1 |
Interactive version: theaggregate.ai/model?slug=varco-vision-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.