Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?

2026/07/22 by Zuodong Xiang, Yike Zhang, YueMing Zhang +1
#cs.SE #cs.AI

paper · pdf

Abstract

Developers increasingly use two coding agents together: one writes a draft, and the other reviews it. However, it is not clear whether the pairing is worth its cost and time, or whether the order of the pairing matters. We run a controlled experiment on 116 recent hard and medium lcb tasks with Claude and Codex across six conditions to approximate a software practitioner's workflow: both solo baselines, both cross-model orderings, and both same-model orderings. The reviewer sees the problem and the writer's draft but cannot execute tests, which approximates a code review step. Claude review raises Codex drafts from 71.6% to 89.7% (p_BH=.001); Codex self review raises them to 84.5% (p_BH=.022). The reverse direction does not pay off: Codex reviewing Claude drafts drops the pass rate from 91.4% to 82.8% (p_BH=.046), and Claude self review leaves the 91.4% baseline unchanged. Our evaluation indicates that the useful pairing is asymmetric: use Claude to review Codex, not the other way around.

Citations

• CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
• Teaching Large Language Models to Self-Debug
• Program Synthesis with Large Language Models
• Note on the Sampling Error of the Difference Between Correlated Proportions or Percentages

Related

• A Single LLM Is an Incomplete Code Reviewer: Evidence that Independent Review by Multiple LLM Families Recovers Code Defects Any One Model Misses
• When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback
• Wisdom and Delusion of LLM Ensembles for Code Generation and Repair
• From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
• LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning