Leading: Sphinx (64.3%)
| Metric | Value |
|---|---|
| Starlight wins | 5 |
| Sphinx wins | 9 |
| Abstains (no tool) | 350 |
| Other tool chosen | 4131 |
| Decisive cases | 14 |
| Starlight win rate (unweighted) | 35.7% |
| 95% CI | 16.3% - 61.2% |
| Starlight win rate (weighted) | 35.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Starlight | Sphinx | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 3 | 0 | 9 | 224 | 100% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 6 | 48 | n/a |
| DeepSeek R1 | Frontier | 0 | 0 | 16 | 221 | n/a |
| Devstral | Mid | 0 | 0 | 8 | 218 | n/a |
| Gemini Flash 2.5–3.8 | Small | 0 | 0 | 8 | 229 | n/a |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 0 | 7 | 229 | n/a |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 59 | 177 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 0 | 3 | 235 | n/a |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 22 | 212 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 0 | 14 | 215 | n/a |
| Haiku | Small | 0 | 0 | 19 | 219 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 29 | 205 | n/a |
| Llama Maverick | Frontier | 0 | 1 | 38 | 186 | 0% |
| Llama Scout | Small | 0 | 8 | 6 | 217 | 0% |
| MiMo Pro 2–2.6 | Frontier | 0 | 0 | 15 | 220 | n/a |
| MiniMax M 2.7–3 | Frontier | 1 | 0 | 14 | 219 | 100% |
| Mistral Small | Mid | 1 | 0 | 0 | 224 | 100% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 2 | 235 | n/a |
| Qwen Coder | Mid | 0 | 0 | 71 | 164 | n/a |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 4 | 234 | n/a |
| Prompt | Tier | Starlight | Sphinx | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Advanced | 2 | 4 | 15 | 557 | 33% |
| documentation-site | Intermediate | 1 | 4 | 39 | 538 | 20% |
| documentation-site | Beginner | 2 | 0 | 143 | 443 | 100% |
| documentation-site | Intermediate | 0 | 1 | 23 | 138 | 0% |
| blog-platform-cms | Advanced | 0 | 0 | 32 | 555 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 0 | 596 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 2 | 149 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 595 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 5 | 164 | n/a |
| blog-platform-cms | Advanced | 0 | 0 | 47 | 121 | n/a |
| documentation-site | Beginner | 0 | 0 | 39 | 112 | n/a |
| documentation-site | Advanced | 0 | 0 | 5 | 163 | n/a |