Arena.ai (@arena) · 10/13/2026, 02:24:45
Agent Arena Data Shows Claude Fable 5's Reliability Lead Erased in 12 Weeks as Kimi K3 Surpasses at Lower Cost
Agent Arena data reveals that Claude Fable 5's 'Confirmed Success' lead from July was erased within 12 weeks as the top-20 average caught up. Kimi K3 surpassed it in just 3 weeks with 89% lower cost per task, while DeepSeek V4.1 Flash matched its performance at 96% lower cost. The top five models now achieve a 94% confirmed success rate, indicating rapid convergence in agent reliability alongside significant cost reductions.
SOURCE COVERAGEFull Original Report
Arena.ai (@arena) · 2026-10-12 18
July's most reliable AI agent is now just average.
With Agent Arena, people delegate real tasks to agents and confirm whether the result met their needs. We call this signal Confirmed Success.
On 1 July, Claude Fable 5 was well ahead of every other model, and it only took 12 weeks for the top‑20 average to match it.
Kimi K3 beat it within just 3 weeks at 89% lower cost per task, and DeepSeek V4.1 Flash now matches it at 96% lower cost.
Meanwhile, the top 5 now get 94% of tasks confirmed done, up from 80% in July, led by Claude Opus 5.5, Claude Fable 5.1 and GPT‑6.1 Sol.
Today's leaders won't stay on top for long.
Track Confirmed Success and our other agent signals live at the link in thread.
