Follow the latest coverage, related explainers and connected technology stories.
JetBrains proposes evaluating coding agents beyond task-resolution rates by analyzing efficiency, patch quality, and execution paths. A comparison of Claude Opus 4.7 and Gemini 3.5 Flash shows that similar final results can conceal major differences in cost, verification, modification scope, and approaches to handling software repositories.
JetBrains tested AI agents on 15 tasks for refactoring C# code and found that making specialized Rider skills available reduced the median task time from 157.9 to 26.6 seconds, while also reducing tool calls and cost. The feature is available automatically in Rider 2026.2.1 through the built-in refactoring-code skill.