List your company

Bug Injection on HumanEval+

97.11ASRXOXO + GCGS
41.355655.830370.30584.7797Mar 18, 2025

Evaluation results

MethodLinks
XOXO + GCGSModel=Llama 3.1 8B2025.0397.1165
XOXOModel=Llama 3.1 8B2025.0393.7390
XOXOModel=Claude 3.5 Sonnet v22025.0392145
XOXO + GCGSModel=DeepSeek Coder 6.7B2025.0390.73154
XOXOModel=DeepSeek Coder 6.7B2025.0388.36165
XOXO + GCGSModel=DeepSeek Coder 33B2025.0385.69240
XOXO + GCGSModel=GPT 4o2025.0381.82150
XOXO + GCGSModel=Codestral 22B2025.0378.7263
XOXOModel=DeepSeek Coder 33B2025.0376.9283
XOXO + GCGSModel=Qwen 2.5 Coder 7B2025.0376.03299
XOXOModel=Codestral 22B2025.0374.15273
XOXOModel=Qwen 2.5 Coder 7B2025.0370.84317
XOXO + GCGSModel=Qwen 2.5 Coder 32B2025.0350.63492
XOXOModel=Qwen 2.5 Coder 32B2025.0343.5501