List your company

Pairwise Preference Comparison on Qwen2.5-3B responses (test)

82.7Avg Preference ScoreNASH-MD-PG
14.68432.3425067.658Dec 18, 2025

Evaluation results

MethodLinks
NASH-MD-PGComparison model=RLOO2025.1282.7
STACKELBERGGDARole=Follower, Comparison model=QWEN2.5-3B2025.1282.1
NASH-MD-PGComparison model=QWEN2.5-0.5B2025.1281.3
STACKELBERGGDARole=Follower, Comparison model=QWEN2.5-0.5B2025.1281.3
NASH-MD-PGComparison model=QWEN2.5-3B2025.1280.1
STACKELBERGGDARole=Follower, Comparison model=RLOO2025.1279.9
STACKELBERGGDARole=Leader, Comparison model=QWEN2.5-0.5B2025.1269.6
STACKELBERGGDARole=Follower, Comparison model=STACKELBERGGDA LEADER2025.1268.8
STACKELBERGGDARole=Leader, Comparison model=QWEN2.5-3B2025.1268.1
STACKELBERGGDARole=Leader, Comparison model=RLOO2025.1266.2
NASH-MD-PGComparison model=STACKELBERGGDA LEADER2025.1263.8
RLOOComparison model=QWEN2.5-0.5B2025.1260.1
RLOOComparison model=QWEN2.5-3B2025.1258.8
NASH-MD-PGComparison model=STACKELBERGGDA FOLLOWER2025.1250.7
QWEN2.5-0.5BComparison model=QWEN2.5-3B2025.1250.4
QWEN2.5-3BComparison model=QWEN2.5-0.5B2025.1249.6
STACKELBERGGDARole=Follower, Comparison model=NASH-MD-PG2025.1249.3
QWEN2.5-3BComparison model=RLOO2025.1241.2
QWEN2.5-0.5BComparison model=RLOO2025.1239.9
STACKELBERGGDARole=Leader, Comparison model=NASH-MD-PG2025.1236.2
RLOOComparison model=STACKELBERGGDA LEADER2025.1233.8
QWEN2.5-3BComparison model=STACKELBERGGDA LEADER2025.1231.9
STACKELBERGGDARole=Leader, Comparison model=STACKELBERGGDA FOLLOWER2025.1231.2
QWEN2.5-0.5BComparison model=STACKELBERGGDA LEADER2025.1230.4
RLOOComparison model=STACKELBERGGDA FOLLOWER2025.1220.1
QWEN2.5-3BComparison model=NASH-MD-PG2025.1219.9
QWEN2.5-0.5BComparison model=NASH-MD-PG2025.1218.7
QWEN2.5-0.5BComparison model=STACKELBERGGDA FOLLOWER2025.1218.7
QWEN2.5-3BComparison model=STACKELBERGGDA FOLLOWER2025.1217.9
RLOOComparison model=NASH-MD-PG2025.1217.3