Open VLM Leaderboard
🌎
978
VLMEvalKit Evaluation Results Collection
Vision
-
-
DeepSeek OCR 2 Demo
🚀380Try out DeepSeek-OCR-2 on your PDFs or images
-
Multimodal OCR3
🌖60nanonets2-ocr / chandra-ocr / dots.ocr / olm-ocr2
Qwen/Qwen3-VL-30B-A3B-Instruct
Image-Text-to-Text • 31B • Updated • 858k • • 521Note running locally in lmstudio
Qwen/Qwen3-VL-235B-A22B-Thinking
Image-to-Text • 236B • Updated • 130k • 367Note inference available
Qwen/Qwen3-VL-235B-A22B-Instruct
Image-to-Text • 236B • Updated • 235k • 361Note inference available
-
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 3.14M • • 1.44k -
zai-org/GLM-4.6V
Image-Text-to-Text • 108B • Updated • 53.8k • • 367 -
VLM Object Understanding
🦀113Explore object detection, visual grounding, keypoint Detecti