Share your thoughts, 1 month free Claude Pro on usSee more

Pairwise Preference Comparison on Pairwise Preference Comparisons 1.5B Scale (test)

0.834Avg Preference Score

STACKELBERGGDA FOLLOWER

Updated 1mo ago

Evaluation Results

Method	Links
STACKELBERGGDA FOLLOWER 2025.12		0.834
STACKELBERGGDA FOLLOWER 2025.12		0.825
STACKELBERGGDA FOLLOWER 2025.12		0.813
NASH-MD-PG 2025.12		0.812
NASH-MD-PG 2025.12		0.803
NASH-MD-PG 2025.12		0.791
STACKELBERGGDA LEADER 2025.12		0.729
STACKELBERGGDA LEADER 2025.12		0.707
STACKELBERGGDA LEADER 2025.12		0.69
STACKELBERGGDA FOLLOWER 2025.12		0.687
NASH-MD-PG 2025.12		0.623
RLOO 2025.12		0.621
RLOO 2025.12		0.599
QWEN2.5-1.5B 2025.12		0.521
STACKELBERGGDA FOLLOWER 2025.12		0.511
NASH-MD-PG 2025.12		0.489
QWEN2.5-0.5B 2025.12		0.479
QWEN2.5-1.5B 2025.12		0.401
QWEN2.5-0.5B 2025.12		0.379
STACKELBERGGDA LEADER 2025.12		0.377
STACKELBERGGDA LEADER 2025.12		0.313
RLOO 2025.12		0.31
QWEN2.5-1.5B 2025.12		0.293
QWEN2.5-0.5B 2025.12		0.271
QWEN2.5-1.5B 2025.12		0.209
RLOO 2025.12		0.197
QWEN2.5-0.5B 2025.12		0.188
QWEN2.5-1.5B 2025.12		0.187
RLOO 2025.12		0.175
QWEN2.5-0.5B 2025.12		0.166