Artificial Analysis Coding Agent Index
The Artificial Analysis Coding Agent Index is a comprehensive benchmark published by Artificial Analysis for evaluating the capabilities of AI models acting as coding agents. It assesses model performance and efficiency across a range of programming tasks.
Timeline (last 90 days)
On Cognition's Frontier Code 2.0, Mistral Large 4 leads at 19.7%; on the Artificial Analysis Coding Agent Index it scores 48%; the Cyber Index is 51%, with a malicious cyber refusal rate of 96.6%
According to the evaluation by the Artificial Analysis Coding Agent Index, Mistral Large 4 scored 48 points.
All Facts (2)
On Cognition's Frontier Code 2.0, Mistral Large 4 leads at 19.7%; on the Artificial Analysis Coding Agent Index it scores 48%; the Cyber Index is 51%, with a malicious cyber refusal rate of 96.6%
50%UnverifiedAccording to the evaluation by the Artificial Analysis Coding Agent Index, Mistral Large 4 scored 48 points.
50%