Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Consistency Evaluation on RealUnify GEU
Loading...
0.32
MC Score
Bagel + SFT
0.2992
0.3046
0.31
0.3154
May 18, 2026
MC Score
CN Score
AF Score
MR Score
Total Score
Updated 15d ago
Evaluation Results
Method
Method
Links
MC Score
CN Score
AF Score
MR Score
Total Score
Bagel + SFT
SFT=true
2026.05
0.32
0.32
0.47
0.34
0.3625
Bagel + Unicot
Enhancement=Unicot
2026.05
0.32
0.4
0.5
0.35
0.3925
Bagel + LatentUMM
Enhancement=LatentUMM
2026.05
0.31
0.39
0.53
0.36
0.3975
Bagel
Description=Base model
2026.05
0.3
0.39
0.52
0.34
0.3875
Feedback
Search any
task
Search any
task