List your company

General Question Answering on OOD Non-Math GPQA and CommonsenseQA

71.4Pass@1Baseline LLM
44.15251.22658.365.374Mar 4, 2026

Evaluation results

MethodLinks
Baseline LLMSystem Category=Standalone2026.0371.47,428100
Brier-SLM-VerbSystem Category=Collaborative2026.0370.37,18878.9
COREA *System Category=Collaborative2026.0369.76,17859
RLVR-SLM-ProbeSystem Category=Collaborative2026.0367.34,72432.7
Router+RLVR-SLMSystem Category=Collaborative2026.0365.43,78134
L1-SLM*System Category=Standalone2026.0364.71,9020
Brier-SLMSystem Category=Standalone2026.0363.51,7080
RLVR-SLM-VerbSystem Category=Collaborative2026.0362.71,5101.1
RLVR-SLM-AvgProbSystem Category=Collaborative2026.0362.51,4880.9
RLVR-SLMSystem Category=Standalone2026.0362.41,4380
SLM-VerbSystem Category=Collaborative2026.0348.82,6099.4
SLMSystem Category=Standalone2026.0345.22,0040