Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Chat Performance on Alpaca-Eval
Loading...
55.8
Score
GR3
33.024
38.937
44.85
50.763
Mar 11, 2026
Score
Token Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Token Count
GR3
Model Backbone=Qwen3–8B
2026.03
55.8
765
GRPO
Model Backbone=Qwen3–8B
2026.03
53.5
1,670
Initial
Model Backbone=Qwen3–8B
2026.03
50.2
778
GR3
Model Backbone=Qwen3–4B
2026.03
44.1
859
Initial
Model Backbone=Qwen3–4B
2026.03
40.1
737
GRPO
Model Backbone=Qwen3–4B
2026.03
33.9
1,993
Feedback
Search any
task
Search any
task
