Grounding and Counting on BLINK count
67.5AccuracyFineViT-VL
Evaluation Results
| Method | Links | |
|---|---|---|
| FineViT-VLLanguage Backbone=Qwen3 1.7B LLM, Evaluation Framework=VLMEvalKit [69]2026.03 | 67.5 | |
| Aquila-VLLanguage Backbone=Qwen2.5 1.5B LLM, Evaluation Framework=VLMEvalKit [69]2026.03 | 66.67 | |
| Intern3.5-VLLanguage Backbone=Qwen3 1.7B LLM, Evaluation Framework=VLMEvalKit [69]2026.03 | 65 | |
| Qwen3-VLLanguage Backbone=Qwen3 1.7B LLM, Evaluation Framework=VLMEvalKit [69]2026.03 | 63.33 |