terminal-bench

Terminal-Bench

Agent completion of tasks in a terminal environment.

Methodology

Scores are shown exactly as published by each source. Source boards are ranked independently and are never averaged.

Independent source results

Epoch AI Benchmarking Hub

Synced by EveryAI: This is the sync time, not the measurement date.

Epoch AI Benchmarking Hub leaderboard
#ModelScore
1Gemini 2.5 Flasheveryais/gemini-2-5-flash17.1%
Terminal-Bench | everyais