Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational Alignment on Alpaca-Evals
Loading...
58.12
Alpaca-Evals Score
ODRPO Gini-Med (GRPO)
53.0344
54.3547
55.675
56.9953
May 12, 2026
Alpaca-Evals Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
Alpaca-Evals Score
ODRPO Gini-Med (GRPO)
Policy Model=Qwen2.5-7...
2026.05
58.12
ODRPO Gini-Med (MaxRL)
Policy Model=Qwen2.5-7...
2026.05
57.21
ODRPO Gini (GRPO)
Policy Model=Qwen2.5-7...
2026.05
57.11
GRPO
Policy Model=Qwen2.5-7...
2026.05
56.91
ODRPO Gini (MaxRL)
Policy Model=Qwen2.5-7...
2026.05
56.91
ODRPO Gini (GRPO)
Policy Model=Qwen3-4B-...
2026.05
56.61
ODRPO Gini-Med (GRPO)
Policy Model=Qwen3-4B-...
2026.05
56.41
ODRPO Gini (MaxRL)
Policy Model=Qwen3-4B-...
2026.05
56.34
ODRPO Gini-Med (MaxRL)
Policy Model=Qwen3-4B-...
2026.05
55.97
MaxRL
Policy Model=Qwen3-4B-...
2026.05
55.33
GRPO
Policy Model=Qwen3-4B-...
2026.05
55.29
MaxRL
Policy Model=Qwen2.5-7...
2026.05
53.23
Feedback
Search any
task
Search any
task