List your company

Vulnerability Detection on Vulnerability Detection synthetic dataset 1.0 (test)

12.78F1 ScoreMulti-turn C-ing Clearly
2.6925.3117.9310.549Dec 16, 2025

Evaluation results

MethodLinks
Multi-turn C-ing ClearlyBackbone=Llama-3.1-8B-Instruct, Token Budget=1B tokens2025.1212.7813.3912.23
C-ing ClearlyBackbone=Llama-3.1-8B-Instruct, Token Budget=1B tokens2025.129.8911.528.66
No C-ingBackbone=Llama-3.1-8B-Instruct, Token Budget=1B tokens2025.124.911.763.09
Llama-3.1-8B-InstructBackbone=Llama-3.1-8B-Instruct, Mode=Zero-shot / Base Model2025.123.081.7811.46