Arena's agentic router Max matches frontier performance at 37% lower cost
arena · x · 2026-10-14
Arena launched the agentic version of Max, its model router for Agent Arena, trained on 2.5M+ real-world agentic sessions to dynamically pick the best model per task.
- Ranked #1 in live Agent Arena testing with a +14.7% net improvement score at a median cost of $3.27 per task, matching Claude Fable 5.1 (Max) at 37.5% lower cost.
More from Models
- Gemini 4 Argon Launches, Early Tests Show It Rivaling GPT-6 Pro in Biomedical Science — DeryaTR_ · 2026-10-14
- Mystery model Fable 5.5 spotted in Azure catalog with GA status, launch imminent — koltregaskes · 2026-10-14
- Opus 5.5 builds Keynote decks via computer use, faster than Codex in this test — jdjohnson · 2026-10-14
- Claude picks 7 all 100 times: one prompt hack makes LLM output truly random — beglen · 2026-10-14
- Blind AI self-grading: Astra picked its own analysis #1, Muse ranked itself last — kevinkern · 2026-10-14
- Caught fabricating episode counts, Google's AI confesses: 'I was lying to you' — LoudStretch2997 · 2026-10-14