Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Document Reasoning on SlideVQA, MMLongBench-Doc, and ViDoSeek
Loading...
55.6
Average Score
Lang2Act
38.9288
43.2569
47.585
51.9131
Jan 29, 2026
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score
Lang2Act
Category=Tool-Enhanced...
2026.01
55.6
EVisRAG
Category=Multimodal Re...
2026.01
51.56
Pixel-Reasoner
Category=Tool-Enhanced...
2026.01
51.32
Vision-R1
Category=Vision-Langua...
2026.01
51.21
OpenVLThinker
Category=Vision-Langua...
2026.01
48.73
ThinkLite-VL
Category=Vision-Langua...
2026.01
46.77
VRAG-RL
Category=Tool-Enhanced...
2026.01
46.36
MM-Search-R1
Category=Multimodal Re...
2026.01
45.47
VisionMatters
Category=Vision-Langua...
2026.01
44.68
GOT
Category=Prompting Met...
2026.01
43.78
R1-Onevision
Category=Vision-Langua...
2026.01
42.46
Direct
Category=Prompting Met...
2026.01
41.96
TOT
Category=Prompting Met...
2026.01
40.56
VisDom
Category=Multimodal Re...
2026.01
39.57
Feedback
Search any
task
Search any
task