Skip to content
Hacker News · AI·· 3 h agoAI score42

Terminal-Bench 4.1 Leaderboard: GitHub Copilot's Copilot Fusion Tops at 71.2%

Terminal-Bench 4.1

AI summary

Terminal-Bench 4.1 ranks GitHub Copilot's Copilot Fusion (max) first at 71.2% ± 2.9%, ahead of Claude Code's Opus 5.5 (max) and Fable 5.2 (max), both at 65.8%. Gemini 4 Carbon (high) on Antigravity CLI follows at 64.5%, while Codex's GPT-6.2 Astra (max) reaches 62.1%. The leaderboard spans 52 model-agent entries with dates, token usage and cost.

Source:Hacker News · AI · tbench.ai