List your company

Binary decision on PLASMA

84.5AccuracyIDEA
48.6257.93567.2576.565Apr 14, 2026

Evaluation results

MethodLinks
IDEAModel=Qwen-3-32B2026.0484.5
IDEAModel=Qwen-3-4B2026.0483.9
CoTModel=GPT-5.22026.0482.9
VanillaModel=Qwen-3-4B2026.0482
IDEA w/o MCModel=Qwen-3-32B2026.0482
VanillaModel=Qwen-3-32B2026.0481.1
IDEA w/o InterModel=Qwen-3-8B2026.0480.2
IDEAModel=Qwen-3-8B2026.0480.2
BIRDModel=Qwen-3-32B2026.0479.9
LogitModel=Qwen-3-32B2026.0479.7
IDEA w/o MCModel=Qwen-3-8B2026.0479.5
IDEA w/o InterModel=Qwen-3-4B2026.0479.3
VanillaModel=Qwen-3-8B2026.0478.1
IDEA w/o InterModel=Qwen-3-32B2026.0476.8
IDEA w/o EMModel=Qwen-3-8B2026.0476.6
LogitModel=Qwen-3-8B2026.0476.4
IDEA w/o EMModel=Qwen-3-32B2026.0476.3
CoTModel=Qwen-3-8B2026.0475.9
IDEA w/o EMModel=Qwen-3-4B2026.0475.7
LogitModel=Qwen-3-4B2026.0475.6
CoTModel=DeepSeek R12026.0475.4
BIRDModel=Qwen-3-4B2026.0475.3
IDEA w/o MCModel=Qwen-3-4B2026.0475.2
CoTModel=Qwen-3-4B2026.0475.1
CoTModel=Qwen-3-32B2026.0473.7
BIRDModel=Qwen-3-8B2026.0473.3
RandomModel=N/A2026.0450