Copilot Fusion claims #1 on Terminal Bench 4.1 at less than half Claude Code's cost

imdigitalashish · x · 2026-11-20

imdigitalashish claims the top spot on Terminal Bench 4.1 at less than half the cost, scoring 5 points above Claude Code. The leaderboard screenshot shows Copilot Fusion (max) via GitHub Copilot at 71.2%±2.9% resolution rate ($2.8k cost), ahead of Opus 5.5 (max) with Claude Code at 65.8%±3.1% ($4.7k) and Fable 5.2 (max) at 65.8%; GPT-6.2, Gemini 4 and Kimi K3.1 Pro variants fill out the 60% band. Third-party claim, not yet independently verified.

Original post →

More from coding & agent

coding & agent channel →