List your company

Three-way probability ranking on COMMON2SENSE paired

76.2F1 (C1)IDEA
26.17639.16352.1565.137Apr 14, 2026

Evaluation results

MethodLinks
IDEAModel=Qwen-3-32B2026.0476.274.557.269.3
IDEA w/o MCModel=Qwen-3-32B2026.0473.2595361.7
IDEAModel=Qwen-3-8B2026.0472.871.165.269.7
IDEA w/o InterModel=Qwen-3-32B2026.0471.569.851.864.4
IDEA w/o EMModel=Qwen-3-32B2026.0470.668.950.163.2
IDEA w/o MCModel=Qwen-3-8B2026.0468.367.148.861.4
IDEA w/o InterModel=Qwen-3-8B2026.0467.56650.161.2
IDEA w/o EMModel=Qwen-3-8B2026.0465.864.247.259.1
PWCModel=Qwen-3-8B2026.0461.552.841.551.9
BIRDModel=Qwen-3-32B2026.045960.237.152.1
IDEAModel=Qwen-3-4B2026.0457.555.338.550.4
BIRDModel=Qwen-3-8B2026.0455.256.734.648.8
PWCModel=Qwen-3-32B2026.0454.856.43348.1
PWCModel=Qwen-3-4B2026.0454.26141.552.2
IDEA w/o MCModel=Qwen-3-4B2026.0453.65133.245.9
IDEA w/o InterModel=Qwen-3-4B2026.0452.249.435.845.8
IDEA w/o EMModel=Qwen-3-4B2026.0450.547.616.838.3
CoTModel=GPT-5.22026.0445.543.829.540.2
VanillaModel=Qwen-3-32B2026.0443.841.530.838.7
VanillaModel=Qwen-3-8B2026.0441.839.230.137
BIRDModel=Qwen-3-4B2026.0439.841.51933.4
VanillaModel=Qwen-3-4B2026.0439.236.128.434.6
CoTModel=Qwen-3-32B2026.0438.236.52733.9
CoTModel=Qwen-3-8B2026.0436.535.224.832.2
CoTModel=Qwen-3-4B2026.0435.232.526.131.3
LogitModel=Qwen-3-32B2026.0434.533.324.930.9
RandomModel=N/A2026.0433.333.333.333.3
LogitModel=Qwen-3-8B2026.0432.231.423.629.1
CoTModel=DeepSeek R12026.0431.833.520.528.6
LogitModel=Qwen-3-4B2026.0428.129.223.827