Model Manifest routes tasks to cut LLM costs by 93% on HumanEval
emeka_boris · x · 2026-09-02
Introducing Model Manifest (MoM), an open protocol where a mom.yaml file decides which model handles each message. In HumanEval tests, it started with Qwen3 Coder Next and escalated hard tasks to Sonnet/Opus. It achieved 164/164 solved problems at a cost of $0.09, down 93% from running Opus alone ($1.34), by avoiding expensive models for simple tasks.
More from coding & agent
- Local e-reader app built with Gemma avoids spoilers, saves battery — DynamicWebPaige · 2026-09-02
- you.com Answer API verifies every citation in source text, hits 93.48% on SimpleQA — RichardSocher · 2026-09-02
- YC-backed Struct launches AI Production Engineer for automated monitoring — ycombinator · 2026-09-02
- Coding harness built on OpenAI's 'secret society' of self-organizing agents — floguo · 2026-09-02
- Developers run fleets of AI agents. Why haven't normal people? — fhinkel · 2026-09-02
- Doberman: MCP proxy with allow/auth/block verdicts — Da_Lil_Fu · 2026-09-02