Arena.ai · @arena · X·2026-09-17 01:49·30分钟前
AI 导读

Arena 实习生 @melissapan 评测 7 个模型在 Claude Code、Codex 和 Pi 三种 harness 下的编码表现,共 21 个模型-harness 组合。

Arena.ai@arena
63AI 编辑部评分,满分 100
2026-09-17 01:49· 30分钟前
AI 导读

Arena 实习生 @melissapan 评测 7 个模型在 Claude Code、Codex 和 Pi 三种 harness 下的编码表现,共 21 个模型-harness 组合。

Do models need their native harness for coding? Awesome work from our intern @melissapan on this. She dug into whether the harness (Claude Code vs Codex CLI vs Pi) actually moves the needle for coding agents.

Turns out it matters way less than people assume. 21 model-harness pairs, real rigor. More from Arena to come.

More details on the Arena blog: https://arena.ai/blog/coding-agents-harness-tax

Melissa PanDoes your Claude model really need Claude Code…? 🤔 We evaluate 7 models on Claude Code, Codex, and Pi. Three surprising findings emerge: 1️⃣Harness choice has ...