Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Personalization on Real-world (test)
Loading...
7.35
Score
PPOpt
5.4156
5.9178
6.42
6.9222
Feb 12, 2026
Score
Delta Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Delta Score
PPOpt
LLM Backbone=GPT-oss-20b
2026.02
7.35
1.86
PPOpt
LLM Backbone=Llama-3-8...
2026.02
7.2
1.71
PPOpt
LLM Backbone=Qwen3-8b
2026.02
7.1
1.61
Vanilla
LLM Backbone=Llama-3-8...
2026.02
5.49
-
Vanilla
LLM Backbone=Qwen3-8b
2026.02
5.49
-
Vanilla
LLM Backbone=GPT-oss-20b
2026.02
5.49
-
Feedback
Search any
task
Search any
task
