Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on PaveInstruct
Loading...
7.28
Judge Score
MiniCPM-V-2.6
3.5152
4.4926
5.47
6.4474
Apr 9, 2026
Judge Score
Pass Rate
Updated 9d ago
Evaluation Results
Method
Method
Links
Judge Score
Pass Rate
MiniCPM-V-2.6
Setting=Trained
2026.04
7.28
72
LLaVA-1.6-7B
Setting=Trained
2026.04
6.96
56
LLaMA-3.2-11B
Setting=Trained
2026.04
6.96
58
InternVL-3.5-8B
Setting=Trained
2026.04
6.86
58
LLaVA-1.5-7B
Setting=Trained
2026.04
6.56
56
PaliGemma-3B
Setting=Zero-shot
2026.04
6.38
62.5
PaveGPT-7B
Setting=Trained
2026.04
6.14
40
MiniCPM-V-2.6
Setting=Zero-shot
2026.04
5.71
39.3
PaliGemma-3B
Setting=Trained
2026.04
5.12
30
InternVL-3.5-8B
Setting=Zero-shot
2026.04
4.86
20
LLaVA-1.6-7B
Setting=Zero-shot
2026.04
4.56
18
LLaVA-1.5-7B
Setting=Zero-shot
2026.04
4.53
30
LLaMA-3.2-11B
Setting=Zero-shot
2026.04
3.66
14
Feedback
Search any
task
Search any
task