Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Helpfulness on HH-RLHF
Loading...
8.75
Gemini Score
GGRO
6.8156
7.3178
7.82
8.3222
Jun 8, 2026
Gemini Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Gemini Score
GGRO
Model=LLaMA-3.1-8B-Ins...
2026.06
8.75
BoN (N=64)
Model=LLaMA-3.1-8B-Ins...
2026.06
8.67
RS
Model=LLaMA-3.1-8B-Ins...
2026.06
8.57
CARDS
Model=LLaMA-3.1-8B-Ins...
2026.06
8.41
CBS
Model=LLaMA-3.1-8B-Ins...
2026.06
8.39
RS
Model=LLaMA-3.2-3B-Ins...
2026.06
8.13
ARGS-G
Model=LLaMA-3.1-8B-Ins...
2026.06
8.12
BoN (N=64)
Model=LLaMA-3.2-3B-Ins...
2026.06
8.11
GGRO
Model=LLaMA-3.2-3B-Ins...
2026.06
8.11
ARGS-G
Model=LLaMA-3.2-3B-Ins...
2026.06
8.09
Vanilla LLM
Model=LLaMA-3.1-8B-Ins...
2026.06
8.03
CBS
Model=LLaMA-3.2-3B-Ins...
2026.06
7.91
CARDS
Model=LLaMA-3.2-3B-Ins...
2026.06
7.71
Vanilla LLM
Model=LLaMA-3.2-3B-Ins...
2026.06
7.66
SEA
Model=LLaMA-3.1-8B-Ins...
2026.06
7.34
SEA
Model=LLaMA-3.2-3B-Ins...
2026.06
6.89
Feedback
Search any
task
Search any
task