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

arXiv: https://arxiv.org/abs/2607.21656 · HTML: https://mlsanity.com/paper/2607.21656/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021)
- [CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation](https://mlsanity.com/paper/2501.07811/) (2025)
- [DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2509.13723/) (2025)
- [The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents](https://mlsanity.com/paper/2605.08060/) (2026)
- [The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management](https://mlsanity.com/paper/2605.23071/) (2026)
- [How Much Can Repeated Running Buy? A Measured Variance Ceiling for LLM Code Evaluation](https://mlsanity.com/paper/2606.00920/) (2026)
- [Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement](https://mlsanity.com/paper/2603.00539/) (2026)
- [SwiftBot: A Decentralized Platform for LLM-Powered Federated Robotic Task Execution](https://mlsanity.com/paper/2603.20233/) (2026)

## Built on by (most cited first, 4 of 4)

- [Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access](https://mlsanity.com/paper/2608.08942/) (2026)
- [Humanize: Judgement Engineering for Agentic Coding](https://mlsanity.com/paper/2610.08900/) (2026)
- [Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study](https://mlsanity.com/paper/2610.10961/) (2026)
- [Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines](https://mlsanity.com/paper/2610.15897/) (2026)

## Abstract (arXiv)

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% (pBH=.001); Codex self review raises them to 84.5% (pBH=.022). The reverse direction does not pay off: Codex reviewing Claude drafts drops the pass rate from 91.4% to 82.8% (pBH=.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.