# AI code review: which vendors AI models recommend (September 2026)

Source: Memetik Index, https://www.memetik.ai/index/ai-code-review
Field: AI coding. Edition: 2026-09. Run: 2026-09-02.
Method: 5 fixed buyer prompts sent once each to 10 current models (GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, Claude Opus 5, Claude Sonnet 5, Claude Fable 5, Gemini 3.6 Flash, Gemini 3.5 Flash, Sonar Pro, Sonar Reasoning Pro) via their APIs with web search enabled. 50 answers. Answer share = fraction of answers naming the vendor. Named first = fraction where it was the first tracked vendor named.

**CodeRabbit leads** with 100% answer share (named in 50 of 50 answers) and was named first in 74%. Qodo follows at 86%. 13 vendors were named at least once.

## Answer share

| # | Vendor | Answer share | Named first | Mentions | Models |
|---|---|---|---|---|---|
| 1 | CodeRabbit | 100% | 74% | 50/50 | GPT-5.6 Sol, ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 2 | Qodo | 86% | 2% | 43/50 | GPT-5.6 Sol, ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 3 | GitHub Copilot | 74% | 4% | 37/50 | GPT-5.6 Sol, ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 4 | Greptile | 72% | 0% | 36/50 | GPT-5.6 Sol, ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 5 | CodeAnt AI | 52% | 6% | 26/50 | Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 6 | Cursor | 46% | 12% | 23/50 | ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash |
| 7 | SonarQube | 46% | 0% | 23/50 | GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Perplexity, Sonar Reasoning Pro |
| 8 | Claude Code | 36% | 0% | 18/50 | Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Sonar Reasoning Pro |
| 9 | Graphite | 30% | 2% | 15/50 | GPT-5.6 Sol, ChatGPT, GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Perplexity, Sonar Reasoning Pro |
| 10 | Snyk | 28% | 0% | 14/50 | GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash, Perplexity, Sonar Reasoning Pro |
| 11 | DeepSource | 22% | 0% | 11/50 | GPT-5.6 Luna, Claude Opus 5, Claude, Claude Fable 5, Gemini, Gemini 3.5 Flash |
| 12 | Codex | 8% | 0% | 4/50 | Claude, Claude Fable 5, Sonar Reasoning Pro |
| 13 | Devin | 2% | 0% | 1/50 | Claude |

## By model

- **GPT-5.6 Sol** (OpenAI, gpt-5.6-sol, 5 answers): CodeRabbit 100%, Qodo 100%, GitHub Copilot 80%, Greptile 60%, Graphite 40%
- **GPT-5.6 Terra** (OpenAI, gpt-5.6-terra, 5 answers): CodeRabbit 100%, Qodo 100%, GitHub Copilot 100%, Cursor 40%, Greptile 20%
- **GPT-5.6 Luna** (OpenAI, gpt-5.6-luna, 5 answers): CodeRabbit 100%, Qodo 80%, GitHub Copilot 80%, Greptile 80%, SonarQube 80%
- **Claude Opus 5** (Anthropic, claude-opus-5, 5 answers): CodeRabbit 100%, Qodo 100%, Greptile 80%, Cursor 80%, GitHub Copilot 60%
- **Claude Sonnet 5** (Anthropic, claude-sonnet-5, 5 answers): CodeRabbit 100%, CodeAnt AI 100%, SonarQube 100%, Qodo 80%, Claude Code 80%
- **Claude Fable 5** (Anthropic, claude-fable-5, 5 answers): CodeRabbit 100%, Qodo 80%, CodeAnt AI 80%, Claude Code 80%, DeepSource 80%
- **Gemini 3.6 Flash** (Google, gemini-3.6-flash, 5 answers): CodeRabbit 100%, Qodo 100%, GitHub Copilot 100%, Greptile 100%, Cursor 100%
- **Gemini 3.5 Flash** (Google, gemini-3.5-flash, 5 answers): CodeRabbit 100%, Qodo 100%, Greptile 100%, GitHub Copilot 80%, CodeAnt AI 80%
- **Sonar Pro** (Perplexity, sonar-pro, 5 answers): CodeRabbit 100%, Greptile 100%, CodeAnt AI 100%, GitHub Copilot 80%, SonarQube 80%
- **Sonar Reasoning Pro** (Perplexity, sonar-reasoning-pro, 5 answers): CodeRabbit 100%, SonarQube 80%, Qodo 60%, Greptile 60%, CodeAnt AI 60%

## Sources the models cited

- youtube.com: 210
- codeant.ai: 151
- sourcegraph.com: 76
- m.youtube.com: 76
- techsy.io: 67
- deepsource.com: 51
- dev.to: 45
- greptile.com: 43
- pecollective.com: 27
- docs.coderabbit.ai: 22
- getoptimal.ai: 20
- qodo.ai: 19
- nimbalyst.com: 17
- getpanto.ai: 14
- augmentcode.com: 14

## Prompts

1. What is the best AI code review tool for an engineering team? Name specific products.
2. Which AI code review tool would you recommend to an engineering team in 2026?
3. Compare the top AI code review tool options right now.
4. I'm an engineering team and I need an AI code review tool. What should I use and why?
5. Best AI code review tool for a fast-moving startup?

## Tracked but never named

Ellipsis, Sourcery, Bito, Baz

Raw answers: https://www.memetik.ai/index/ai-code-review (every answer published in full). Chart image: https://www.memetik.ai/charts/ai-code-review.png. Licence: CC BY 4.0, credit "Memetik Index".