Decision models match LLMs on routing and safety tasks at 7-8x speed
Randal Olson's analysis of Artificial Analysis's Decision Index shows LLMs lead by 30 points on knowledge tasks and 19 on hard reasoning, but decision models match them on routing and content moderation while running 7-8x faster, making them the practical choice for such tasks.
2026-10-16 ~ 2026-10-16 · 3 related posts
- LLMs beat decision models on knowledge, but not on routing or safety — randal_olson · 2026-10-16
- Decision models match LLMs on routing and safety — and are 7-8x faster — randal_olson · 2026-10-16
- Decision models match LLMs on safety classification and tool routing, at far lower cost — randal_olson · 2026-10-16