Open-weight coding-agent router hits 79.8% on Terminal-Bench 2.1 for $76
kimmonismus · x · 2026-07-25
Open-sourced coding-agent router model Dari says it reached 79.8% on Terminal-Bench 2.1 with only $76 total inference cost.
- It routes each step to the cheapest model that can still change the outcome, and also accounts for cache effects so it avoids unnecessary switching.
- The launch post says frontier setups on the same 89-task suite can cost thousands of dollars.
- It runs inside Claude Code, Codex, and Pi.
- Users can bring their own Anthropic and OpenAI subscriptions, and the weights are on Hugging Face.
More from coding & agent
- Hugging Face wraps 6-month Training Agents series with open recordings and code — SergioPaniego · 2026-10-26
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26