Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Social Dialogue on SOTOPIA Overall (AVG)
Loading...
5.63
AVG Score
Llama-8B+BC+SDPO
4.1948
4.5674
4.94
5.3126
Jan 3, 2025
AVG Score
Updated 4d ago
Evaluation Results
Method
Method
Links
AVG Score
Llama-8B+BC+SDPO
Alignment=BC + Segment...
2025.01
5.63
Llama-8B+BC+ETO
Alignment=BC + ETO
2025.01
5.45
Llama-8B+BC+DMPO
Alignment=BC + DMPO
2025.01
5.43
Llama-8B+BC+DPO
Alignment=BC + DPO
2025.01
5.34
GPT-4-turbo
2025.01
5.32
GPT-4o
2025.01
5.17
Llama-8B+BC+Preferred-SFT
Alignment=BC + Preferr...
2025.01
5.17
Llama-8B+BC
Alignment=Behavioral C...
2025.01
5.16
Llama-8B
2025.01
4.78
GPT-4o-mini
2025.01
4.66
GPT-3.5-turbo
2025.01
4.25
Feedback
Search any
task
Search any
task