Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning Quality on PRIST
Loading...
3.9
PR Score
MIRAS
2.548
2.899
3.25
3.601
Feb 13, 2025
PR Score
LC Score
CC Score
TR Score
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
PR Score
LC Score
CC Score
TR Score
Win Rate
MIRAS
Training Stage=Stage-2
2025.02
3.9
3.76
3.83
3.69
42
LISA
Fine-tuned=true
2025.02
3.76
3.69
3.71
3.58
36
PixelLM
Fine-tuned=true
2025.02
3.35
3.48
3.32
3.28
32
OMG-LLaVA
Fine-tuned=true
2025.02
2.6
2.48
2.58
2.33
24
Feedback
Search any
task
Search any
task