Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Personalized Preference Modeling on Summarize from Human Feedback (test)
Loading...
66.01
Mean Accuracy
EXACT
53.5612
56.7931
60.025
63.2569
Feb 6, 2026
Mean Accuracy
Standard Deviation
Updated 5mo ago
Evaluation Results
Method
Method
Links
Mean Accuracy
Standard Deviation
EXACT
Base Model=Gemma-2-9B-it
2026.02
66.01
0.13
EXACT
Base Model=Llama-3.1-8B
2026.02
65.12
0.14
Base
Base Model=Gemma-2-9B-it
2026.02
63.58
0.18
Reward
Base Model=Qwen2.5-7B-...
2026.02
60.75
0.21
EXACT
Base Model=Qwen2.5-7B-...
2026.02
60.28
0.15
Drift
Base Model=Llama-3.1-8B
2026.02
58.68
0.13
Drift
Base Model=Gemma-2-9B-it
2026.02
58.21
0.12
Base
Base Model=Llama-3.1-8B
2026.02
57.54
0.18
Drift
Base Model=Qwen2.5-7B-...
2026.02
55.63
0.16
Reward
Base Model=Gemma-2-9B-it
2026.02
54.33
0.13
Reward
Base Model=Llama-3.1-8B
2026.02
54.21
0.15
Base
Base Model=Qwen2.5-7B-...
2026.02
54.04
0.12
Feedback
Search any
task
Search any
task
