Benchmark编程Agent指数
Coding Agent Index
A comprehensive benchmark for evaluating AI coding agents, published by Artificial Analysis. It is primarily based on standardized task sets such as SWE-bench and assesses agent performance on coding tasks in realistic software engineering scenarios.
Timeline (last 90 days)
Oct 21
Artificial Analysis evaluated Devinfusion: with Claude Opus 5.5 as the primary model and GPT-6 Luna as an auxiliary model working in parallel, it scored about 68 on its Coding Agent Index, roughly 2 points higher than the specified Claude Code combination, at 31% lower cost per task.
Unverified50%