Visual Question Answering on CII-Bench
44.7AccuracyOurs
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OursBackbone=Qwen2.5-VL-3B2026.01 | 44.7 | 72.5 | 24.8 | |
| GoTVenue=AAAI'24, Backbone=Qwen2.5-VL-3B2026.01 | 39.9 | 72.1 | 24.3 | |
| LADVenue=arXiv'25, Backbone=Qwen2.5-VL-3B2026.01 | 39.1 | 49.7 | 29.6 | |
| CoT-SCVenue=ICLR'23, Backbone=Qwen2.5-VL-3B2026.01 | 37.3 | 57.5 | 29.9 | |
| CoTVenue=NIPS'22, Backbone=Qwen2.5-VL-3B2026.01 | 36.2 | 69.4 | 28.3 | |
| DDCoTVenue=NIPS'23, Backbone=Qwen2.5-VL-3B2026.01 | 35.3 | 63.6 | 33.7 | |
| ToTVenue=NIPS'23, Backbone=Qwen2.5-VL-3B2026.01 | 34.9 | 61.1 | 35.4 | |
| CCoTVenue=CVPR'24, Backbone=Qwen2.5-VL-3B2026.01 | 32.9 | 67.2 | 30.4 |