Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Question Answering on PBSBench Slide-level 1.0 (test)
Loading...
36
BLEU-1
PBS-VL
1.68
10.59
19.5
28.41
Apr 19, 2026
BLEU-1
ROUGE-L
Similarity Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-1
ROUGE-L
Similarity Score
PBS-VL
Framework=Slide-level,...
2026.04
36
39
76
GPT-4o
Input=30 random patches
2026.04
17
20
73
SlideChat
Model type=Pathology-s...
2026.04
16
20
62
Claude-4.5
Input=30 random patches
2026.04
15
18
67
Gemini-2.5-pro
Input=30 random patches
2026.04
9
12
68
HistoGPT
Model type=Pathology-s...
2026.04
3
4
15
Feedback
Search any
task
Search any
task