Terminal-Bench (Terminal Agent Tasks) 排行榜
Tests AI models on complex terminal-based tasks including shell commands, debugging, system administration, and multi-step CLI workflows.
为什么重要： Measures agentic capability in terminal environments — critical for AI coding assistants that execute commands and manage development workflows.
顶级模型
61.7%
Composer 2
平均评分
61.7%
共1个模型
已测试模型
1
指标: pass rate
人类基准
-
评分范围: 0%–100%
Terminal-Bench Scores - Top 1 Models
Ranked by Terminal-Bench score (%)
模型排名
All models with a reported Terminal-Bench score, ranked by highest pass rate.
关于 Terminal-Bench
- 全名
- Terminal-Bench (Terminal Agent Tasks)
- 类别
- Coding
- 指标
- pass rate (%)
- 评分范围
- 0%–100%
- 人类基准
- 尚未确定
- 状态
- 启用
Terminal-Bench is a standardized evaluation that measures AI model performance on specific tasks. It provides comparable scores across different models, helping developers choose the right model for their needs.
Composer 2 currently holds the top score on the Terminal-Bench benchmark. See our full rankings table above for the complete leaderboard with 1 models.
We update benchmark data from multiple sources including HuggingFace open-source model leaderboards and LMArena. Scores are refreshed regularly as new evaluations are published and new models are released.
No. While Terminal-Bench is an important indicator, real-world performance depends on many factors including pricing, latency, context window, and specific task requirements. We recommend using our composite score which weighs multiple benchmarks and practical factors.