List your company

Binary Classification on GSS United States (test)

0.5636AccuracyOG-MAR
0.4691680.4936840.51820.542716Jan 29, 2026

Evaluation results

MethodLinks
OG-MARBackbone=EXAONE 3.52026.010.5636
ValuesRAGBackbone=GPT-4o mini2026.010.5589
ValuesRAGBackbone=EXAONE 3.52026.010.552
DebateBackbone=GPT-4o mini2026.010.5509
OG-MARBackbone=Gemini 2.5 Flash Lite2026.010.5489
OG-MARBackbone=GPT-4o mini2026.010.548
DebateBackbone=EXAONE 3.52026.010.5407
ValuesRAGBackbone=Gemini 2.5 Flash Lite2026.010.5376
RoleBackbone=EXAONE 3.52026.010.5326
OG-MARBackbone=QWEN 2.52026.010.5325
Zero-shotBackbone=EXAONE 3.52026.010.5311
Self-consistencyBackbone=EXAONE 3.52026.010.5266
ValuesRAGBackbone=QWEN 2.52026.010.5215
RoleBackbone=GPT-4o mini2026.010.5184
DebateBackbone=QWEN 2.52026.010.5174
Zero-shotBackbone=GPT-4o mini2026.010.5164
DebateBackbone=Gemini 2.5 Flash Lite2026.010.5138
Zero-shotBackbone=QWEN 2.52026.010.5069
RoleBackbone=QWEN 2.52026.010.5037
RoleBackbone=Gemini 2.5 Flash Lite2026.010.4992
Self-consistencyBackbone=QWEN 2.52026.010.4975
Zero-shotBackbone=Gemini 2.5 Flash Lite2026.010.4957
Self-consistencyBackbone=GPT-4o mini2026.010.492
Self-consistencyBackbone=Gemini 2.5 Flash Lite2026.010.4728