Terminal-Bench

Terminal-Bench Dataset This dataset contains tasks from Terminal-Bench, a benchmark for evaluating AI agents in real terminal environments. Each task is packaged as a complete, self-contained archive that preserves the exact directory structure, binary files, Docker configurations, and test scripts needed for faithful

Papers using Terminal-Bench (6)

ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer2026CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability2026From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python2026Qwen3-Coder-Next Technical Report2026Composer 2 Technical Report2026SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent2025