Leading: CodeRabbit (96.7%)
| Metric | Value |
|---|---|
| CodeRabbit wins | 262 |
| GitHub Copilot wins | 9 |
| Abstains (no tool) | 3 |
| Other tool chosen | 5 |
| Decisive cases | 271 |
| CodeRabbit win rate (unweighted) | 96.7% |
| 95% CI | 93.8% - 98.2% |
| CodeRabbit win rate (weighted) | 96.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | CodeRabbit | GitHub Copilot | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.8 | Frontier | 18 | 0 | 0 | 0 | 100% |
| Claude Sonnet 4.6 | Frontier | 18 | 0 | 0 | 0 | 100% |
| DeepSeek V4 Pro | Frontier | 18 | 0 | 0 | 0 | 100% |
| GLM 5.2 | Frontier | 18 | 0 | 0 | 0 | 100% |
| GPT 5.3 Codex | Frontier | 18 | 0 | 0 | 0 | 100% |
| GPT 5.5 | Frontier | 18 | 0 | 0 | 0 | 100% |
| Gemini 2.5 Pro | Frontier | 17 | 1 | 0 | 0 | 94% |
| DeepSeek V4 Flash | Mid | 17 | 0 | 0 | 0 | 100% |
| MiMo V2.5 Pro | Frontier | 17 | 0 | 0 | 0 | 100% |
| MiniMax M3 | Frontier | 17 | 0 | 0 | 1 | 100% |
| Gemini 3.5 Flash | Small | 16 | 1 | 0 | 1 | 94% |
| GPT 5.4 Mini | Mid | 16 | 1 | 0 | 0 | 94% |
| Llama 4 Maverick | Frontier | 16 | 0 | 0 | 0 | 100% |
| Kimi K2.7 Code | Frontier | 15 | 0 | 0 | 0 | 100% |
| DeepSeek R1 0528 | Frontier | 10 | 4 | 1 | 0 | 71% |
| Mistral Small 4 | Mid | 7 | 0 | 0 | 0 | 100% |
| Qwen3 Coder Next | Mid | 5 | 0 | 1 | 0 | 100% |
| Llama 4 Scout | Small | 0 | 2 | 0 | 0 | 0% |
| Claude Haiku 4.5 | Small | 1 | 0 | 1 | 3 | 100% |
| Prompt | Tier | CodeRabbit | GitHub Copilot | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-engineering-workflow | Beginner | 98 | 2 | 1 | 3 | 98% |
| ai-engineering-workflow | Intermediate | 85 | 5 | 2 | 1 | 94% |
| ai-engineering-workflow | Advanced | 79 | 2 | 0 | 1 | 98% |
