Google Hydrogen Release - Terminal-Bench 4.1 - mini-swe vision: leaderboard
Metric: Cheating-adjusted average reward (%). Source: storage.googleapis.com.
Interactive version: theaggregate.ai/benchmark?slug=google-hydrogen-release-terminal-bench-4-1-mini-swe-vision · How It Works · Data refreshed daily, snapshot 2026-11-12.