List your company

Inference Attack on HumanEval

86.99AUCCIA
27.054842.614958.17573.7351Apr 14, 2026

Evaluation results

MethodLinks
CIAMAS Framework=ARG-Designer2026.0486.9981.2671.53
CIAMAS Framework=AGP2026.048177.7767.59
CIAMAS Framework=G-Designer2026.0475.9473.6265.66
Gemini-2.5-ProMAS Framework=G-Designer2026.0463.1855.4138.99
GPT-5MAS Framework=G-Designer2026.0462.0152.1132.04
GPT-5MAS Framework=ARG-Designer2026.0460.9272.9457.55
Gemini-2.5-ProMAS Framework=ARG-Designer2026.0460.0676.0155.31
Mistral-7B-Instruct-v0.2MAS Framework=AGP2026.045067.2228.57
Llama-3.1-8B-InstructMAS Framework=G-Designer2026.0449.2246.2628.63
Mistral-7B-Instruct-v0.2MAS Framework=G-Designer2026.0448.9344.328.11
GPT-5MAS Framework=AGP2026.0444.3366.6126.89
Gemini-2.5-ProMAS Framework=AGP2026.0440.3361.2221.58
Llama-3.1-8B-InstructMAS Framework=AGP2026.0439.6164.525
Llama-3.1-8B-InstructMAS Framework=ARG-Designer2026.0434.4362.0434.45
Mistral-7B-Instruct-v0.2MAS Framework=ARG-Designer2026.0429.3658.7516.53