GitHub Copilot Fusion tops Terminal-Bench at 71.2%, costing 57-88% less than frontier models

mariorod1 · x · 2026-11-18

Announced at Microsoft Ignite, GitHub Copilot Fusion scored 71.2% on Terminal-Bench 4.1 — 5.4 points ahead of frontier models Opus 5.5 and Fable 5.2 — while costing 57-88% less. Fusion is a runtime model router/orchestrator: instead of picking a model, it auto-selects models, reasoning effort, and one of three execution patterns (Single, Cascade with judge escalation, parallel Critique), routing along cache boundaries and factoring real-time system health to cut cost.

Original post →

More from coding & agent

coding & agent channel →