Yam Peleg CLI Agents Field Report
Used Claude Code, Codex CLI, and Gemini CLI as daily drivers for one week covering coding, research, sysadmin, and automation. Claude Code has the best CLI, Codex is best for 'fire and forget' coding tasks, Gemini has the best web search.
3
Skills
2025-12
Verified
Persona
Skills in this bundle
Claude Code
Anthropic's official agentic coding CLI. Terminal-native, tool-use-driven, with deep file system and shell access. #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue (fastest enterprise SaaS to $1B ARR). 8M+ npm weekly downloads. Opus 4.6 with 1M context.
★ 80K+
Codex CLI
OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (GPT-5.3-Codex), SWE-bench Pro standardized 41.04%. 3-4x more token-efficient than Claude Code, 60-75% cheaper per task. Free with ChatGPT subscription, sandbox-first execution, 619 releases in 10 months.
★ 66K+
Gemini CLI
Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (1K req/day). 97.9K stars, 444 contributors. SWE-bench Pro standardized 43.30% (#2 behind Claude Code).
★ 98K+
Build your own stack.
See all ranked skills and find the best fit for your workflow.
Source
X post: 'CLI Agents | Week 1 Field Report: Claude Code vs Codex-max vs Gemini 3'
View source →Last verified: 2025-12