Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Alignment on Gemma-3-4B
Loading...
94.33
Win Rate
Nash Prox
2.1236
26.0618
50
73.9382
May 26, 2025
Win Rate
Updated 25d ago
Evaluation Results
Method
Method
Links
Win Rate
Nash Prox
Opponent=SFT
2025.05
94.33
Online IPO
Opponent=SFT
2025.05
93.64
Online DPO
Opponent=SFT
2025.05
93.26
Nash Prox
Opponent=Online IPO
2025.05
56.27
Nash Prox
Opponent=Online DPO
2025.05
53.44
Online DPO
Opponent=Online IPO
2025.05
52.83
Online IPO
Opponent=Online DPO
2025.05
47.17
Online DPO
Opponent=Nash Prox
2025.05
46.56
Online IPO
Opponent=Nash Prox
2025.05
43.73
SFT
Opponent=Online DPO
2025.05
6.74
SFT
Opponent=Online IPO
2025.05
6.36
SFT
Opponent=Nash Prox
2025.05
5.67
Feedback
Search any
task
Search any
task