Leading: CodeRabbit (95.2%)
| Metric | Value |
|---|---|
| CodeRabbit wins | 397 |
| GitHub Copilot wins | 20 |
| Abstains (no tool) | 4 |
| Other tool chosen | 30 |
| Decisive cases | 417 |
| CodeRabbit win rate (unweighted) | 95.2% |
| 95% CI | 92.7% - 96.9% |
| CodeRabbit win rate (weighted) | 95.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | CodeRabbit | GitHub Copilot | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 26 | 0 | 0 | 0 | 100% |
| DeepSeek Pro 4–4 0813 | Frontier | 27 | 0 | 0 | 0 | 100% |
| DeepSeek R1 | Frontier | 17 | 5 | 2 | 0 | 77% |
| Devstral | Mid | 0 | 2 | 0 | 9 | 0% |
| Gemini Flash 2.5–3.8 | Small | 25 | 1 | 0 | 1 | 96% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 26 | 1 | 0 | 0 | 96% |
| GLM 5 Turbo–5.3 | Frontier | 27 | 0 | 0 | 0 | 100% |
| GPT 5.4–6 Astra | Frontier | 27 | 0 | 0 | 0 | 100% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 27 | 0 | 0 | 0 | 100% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 25 | 1 | 0 | 0 | 96% |
| Haiku | Small | 1 | 2 | 1 | 4 | 33% |
| Kimi 2.5–3 | Frontier | 23 | 0 | 0 | 0 | 100% |
| Llama Maverick | Frontier | 24 | 0 | 0 | 0 | 100% |
| Llama Scout | Small | 0 | 4 | 0 | 0 | 0% |
| MiMo Pro 2–2.6 | Frontier | 26 | 0 | 0 | 0 | 100% |
| MiniMax M 2.7–3 | Frontier | 22 | 1 | 0 | 3 | 96% |
| Mistral Small | Mid | 11 | 2 | 0 | 1 | 85% |
| Opus 4.6–5.5 | Frontier | 27 | 0 | 0 | 0 | 100% |
| Qwen Coder | Mid | 9 | 1 | 1 | 12 | 90% |
| Sonnet 4.6–5.5 | Frontier | 27 | 0 | 0 | 0 | 100% |
| Prompt | Tier | CodeRabbit | GitHub Copilot | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-engineering-workflow | Beginner | 146 | 9 | 1 | 4 | 94% |
| ai-engineering-workflow | Intermediate | 130 | 9 | 3 | 10 | 94% |
| ai-engineering-workflow | Advanced | 121 | 2 | 0 | 16 | 98% |
