List your company

Code Simulation on CruxEval-O

62.7Pass@1SEC
13.09225.97138.8551.729Jun 23, 2026

Evaluation results

MethodLinks
SECBackbone=Qwen3-4B-Base, Seeds=12026.0662.7
TACBackbone=Qwen3-4B-Base, Seeds=12026.0662.1
RandomBackbone=Qwen3-4B-Base, Seeds=12026.0647.6
M2OBackbone=Qwen3-1.7B2026.0641.5
TACBackbone=Qwen3-1.7B2026.0639.5
M2OBackbone=Llama3.2-3B2026.0637.4
RandomBackbone=Llama3.2-3B2026.0636.2
SECBackbone=Qwen3-1.7B2026.0635.8
TACBackbone=Qwen3-0.6B-Base, Seeds=12026.0635.6
TACBackbone=Llama3.2-3B2026.0635.5
SECBackbone=Qwen3-0.6B-Base, Seeds=12026.0635.2
RandomBackbone=Qwen3-1.7B2026.0634.8
SECBackbone=Llama3.2-3B2026.0634
RandomBackbone=Qwen3-0.6B-Base, Seeds=12026.0628.6
BaseBackbone=Llama3.2-3B2026.0627.6
BaseBackbone=Qwen3-1.7B2026.0615