List your company
ResearchFormerly WizWand

AI-assisted Programming on ConsistencyChecker Programming benchmark

85.1Consistency ScoreQwen-2.5
59.41266.08172.7579.419Jun 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Qwen-2.5Size=32B2025.0685.1
LLaMA-3.1Size=70B2025.0683.5
Qwen-2.5Size=14B2025.0679.9
Qwen-2.5Size=72B2025.0677
GPT-4o-mini2025.0676.5
Qwen-2.5Size=7B2025.0671.7
Qwen-2.5Size=1.5B2025.0663.4
LLaMA-3.1Size=8B2025.0660.4