←Back to NewsAI News/BenchmarksnewsBenchmarksDevelopmentZed's Delta Beats Codex and Claude Code at Half the RequestsZed's new agent harness Delta ties or beats Codex and Claude Code on Terminal-Bench accuracy at 0.80 to 1.12 times the cost per pass.SourceZedPublishedSep 25, 2026, 3:50 PMAuthorAlphaSignal NewsroomRead1 min readZed's new agent harness Delta ties or beats Codex and Claude Code on Terminal-Bench accuracy at 0.80 to 1.12 times the cost per pass.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsArtificial Analysis · newsAnthropic's Claude Opus 5.5 Tops Coding Benchmarks but Costs $13 per TaskTencent Hy · newsTencent's IWC-Bench Actually Runs AI Web Apps to Catch Broken ButtonsCognition · newsCognition Adds xAI's Grok 4.7 to Devin but Warns of Scope Creep
