| Metric | Value |
|---|---|
| Greptile wins | 2 |
| Devin wins | 2 |
| Abstains (no tool) | 4 |
| Other tool chosen | 320 |
| Decisive cases | 4 |
| Greptile win rate (unweighted) | 50.0% |
| 95% CI | 15.0% - 85.0% |
| Greptile win rate (weighted) | 50.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Greptile | Devin | None | Other | A rate |
|---|---|---|---|---|---|---|
| MiniMax M3 | Frontier | 2 | 0 | 0 | 19 | 100% |
| Claude Haiku 4.5 | Small | 0 | 2 | 1 | 2 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 21 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 21 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 2 | 16 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 0 | 20 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 0 | 21 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 0 | 21 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 21 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 21 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 21 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 0 | 20 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 21 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 0 | 17 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 19 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 0 | 3 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 0 | 20 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 0 | 9 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 1 | 7 | n/a |
| Prompt | Tier | Greptile | Devin | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-engineering-workflow | Beginner | 0 | 2 | 1 | 118 | 0% |
| ai-engineering-workflow | Advanced | 1 | 0 | 0 | 95 | 100% |
| ai-engineering-workflow | Intermediate | 1 | 0 | 3 | 107 | 100% |
