OpenVLM VCR: leaderboard
OpenCompass OpenVLM evaluation of VCR: visual clue reasoning over English and Chinese examples, scored with exact match and Jaccard metrics for easy and hard visual reasoning questions.
Metric: Overall Jaccard (%). Source: visualcommonsense.com. Source: huggingface.co. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 VL 7B | 75.6 | #750 |
| 2 | Qwen 2 VL 2B | 61.3 | #1220 |
| 3 | Gemini 1.5 Pro | 38.1 | #445 |
| 4 | Claude 3.5 Sonnet | 35.6 | #350 |
| 5 | MiniCPM-V-2.6 | 33.7 | #836 |
| 6 | InternVL2-8B | 28.6 | #817 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-vcr · How It Works · Data refreshed daily, snapshot 2026-10-20.