302 AI models ranked on TerminalBench Hard. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.
Top model today
GPT-5.6 Sol (OpenAI) leads at 66%, from $5.00 per 1M input.
Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.
Prices are on-demand list rates. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage.
Frequently asked questions
What is the TerminalBench Hard benchmark?
The hardest subset of the Terminal-Bench agentic benchmark, made up of the tasks frontier models complete least often across software engineering, sysadmin, data processing, ML and security. An agent is given an English task and a sandboxed container terminal, and is scored by the pass rate of automated verification tests.
Which AI model scores highest on TerminalBench Hard?
GPT-5.6 Sol (OpenAI) leads with 66%, from $5.00 per 1M input tokens.
How many models are ranked on TerminalBench Hard?
302 models carry a TerminalBench Hard score. Scores come from Artificial Analysis; where a model has a live API price it is verified against LiteLLM and OpenRouter, and models with no current price are listed without one.
OpenAI
Anthropic
Google
Zhipu
Alibaba
DeepSeek
Meta
Moonshot
Xiaomi
MiniMax
xAI
NVIDIA