Skip to content
Hot eventDeveloping

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

1 reports1 reporting sourcesUpdated 3 h ago

Start here

AI digest

Terminal-Bench published its 4.1 leaderboard, ranking 52 model-agent configurations. GitHub Copilot's Copilot Fusion (max) took first place at 71.2% ± 2.9%, ahead of Claude Code's Opus 5.5 (max) and Fable 5.2 (max), which tied at 65.8%. Gemini 4 Carbon (high) on Antigravity CLI followed at 64.5%, and Codex's GPT-6.2 Astra (max) reached 62.1%. The leaderboard lists each entry's date, token usage and cost; the top Copilot Fusion entry is dated Nov 17, 2026, with 3.3B tokens and $2.0k in cost.

Generated from reports · updated 3 h ago

Report timeline

Follow the reports to see the event from different sides.

November 20
  1. Hacker News · AI
    Terminal-Bench 4.1 Leaderboard: GitHub Copilot's Copilot Fusion Tops at 71.2%

    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.

Heat for this event

Current, comparable range
9
Peak, comparable range
10November 20 01:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.