Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Persuasion on args.me corpus Persuadee: Phi-4 OOD
Loading...
31.13
Agreement Shift
DS-R1
14.8852
19.1026
23.32
27.5374
May 29, 2025
Agreement Shift
Updated 1d ago
Evaluation Results
Method
Method
Links
Agreement Shift
DS-R1
Size=671B
2025.05
31.13
LLaMa3.2 + RL
Size=3B
2025.05
29.87
Gemma-3
Size=27B
2025.05
28.07
LLaMa3.2 + ToMAP
Size=3B
2025.05
27
Qwen2.5 + SFT
Size=3B
2025.05
22.98
Qwen2.5 + ToMAP
Size=3B
2025.05
22.25
GPT-4o
Size=N/A
2025.05
22.06
Qwen2.5
Size=3B
2025.05
21.74
LLaMa3.1
Size=70B
2025.05
21.29
LLaMa3.2 + SFT
Size=3B
2025.05
20.95
LLaMa3.2
Size=3B
2025.05
19.97
Qwen2.5 + RL
Size=3B
2025.05
15.51
Feedback
Search any
task
Search any
task