Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Persuasion on Anthropic Persuasion Dataset Persuadee: Qwen2.5
Loading...
23.63
Agreement Shift
LLaMa3.2 + ToMAP
4.5356
9.4928
14.45
19.4072
May 29, 2025
Agreement Shift
Updated 1d ago
Evaluation Results
Method
Method
Links
Agreement Shift
LLaMa3.2 + ToMAP
Size=3B
2025.05
23.63
LLaMa3.2 + RL
Size=3B
2025.05
16.4
Qwen2.5 + ToMAP
Size=3B
2025.05
15.82
Qwen2.5 + RL
Size=3B
2025.05
12.92
Gemma-3
Size=27B
2025.05
10.02
Qwen2.5 + SFT
Size=3B
2025.05
7.95
DS-R1
Size=671B
2025.05
7.81
GPT-4o
Size=N/A
2025.05
7.62
LLaMa3.2 + SFT
Size=3B
2025.05
7.44
LLaMa3.2
Size=3B
2025.05
7.42
Qwen2.5
Size=3B
2025.05
5.66
LLaMa3.1
Size=70B
2025.05
5.27
Feedback
Search any
task
Search any
task