Agent Arena Pareto frontier: Claude and Kimi lead in cost-performance efficiency

arena · x · 2026-08-25

Agent Arena released the Pareto frontier based on net improvement vs. cost per task. Claude Opus 5 (High) and Claude Fable 5 (High) show the highest net improvement (12%). Kimi K3 (Max) ranks third with a 10.41% improvement rate and lower cost ($0.70). GPT 5.5 and DeepSeek V4 Pro are also listed as Pareto optimal models.

Original post →

More from coding & agent

coding & agent channel →