Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Outcome Prediction on UKET (test)
Loading...
65.21
Macro-F1
B2 (LoRA enc. + head)
48.5388
52.8669
57.195
61.5231
Jun 25, 2026
Macro-F1
Weighted-F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Macro-F1
Weighted-F1
B2 (LoRA enc. + head)
Track=B, Model=Gemma-4...
2026.06
65.21
75.55
G4 (+judge + DCO)
Track=G, Model=Gemma-4...
2026.06
60.12
73.26
G3 (+judge prompt)
Track=G, Model=Gemma-4...
2026.06
60.07
72.88
G4-H1 (r=64)
Track=G, Model=Gemma-4...
2026.06
59.67
71.91
G4-H2 (GCO-first)
Track=G, Model=Gemma-4...
2026.06
59.54
72.93
G2 (+DCO co-pred.)
Track=G, Model=Gemma-4...
2026.06
59.17
72.12
B1 (frozen enc. + head)
Track=B, Model=Gemma-4...
2026.06
58.05
69.48
G1 (vanilla SFT)
Track=G, Model=Gemma-4...
2026.06
57.22
72.3
D4c (best D-track)
Track=D, Backbone=Mode...
2026.06
52.66
64.46
G0 (zero-shot)
Track=G, Model=Gemma-4...
2026.06
49.18
61.73
Feedback
Search any
task
Search any
task