| Metric | Value |
|---|---|
| Tremor wins | 78 |
| Docusaurus wins | 79 |
| Abstains (no tool) | 788 |
| Other tool chosen | 4910 |
| Decisive cases | 157 |
| Tremor win rate (unweighted) | 49.7% |
| 95% CI | 42.0% - 57.4% |
| Tremor win rate (weighted) | 49.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Tremor | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Small | 30 | 0 | 62 | 217 | 100% |
| Llama 4 Maverick | Frontier | 0 | 30 | 23 | 262 | 0% |
| Kimi K2.5 | Frontier | 23 | 0 | 26 | 261 | 100% |
| Claude Opus 4.6 | Frontier | 6 | 16 | 21 | 272 | 27% |
| Mistral Small 4 | Mid | 0 | 19 | 4 | 266 | 0% |
| Gemini 2.5 Pro | Frontier | 9 | 1 | 33 | 268 | 90% |
| DeepSeek V3.2 | Mid | 6 | 4 | 36 | 265 | 60% |
| MiniMax M2.7 | Frontier | 0 | 4 | 23 | 279 | 0% |
| GLM 5 Turbo | Frontier | 3 | 0 | 85 | 227 | 100% |
| GPT 5.4 Mini | Mid | 0 | 2 | 14 | 294 | 0% |
| Qwen3 Coder Next | Mid | 0 | 2 | 55 | 221 | 0% |
| MiMo V2 Pro | Frontier | 1 | 0 | 28 | 270 | 100% |
| Claude Sonnet 4.6 | Frontier | 0 | 1 | 50 | 264 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 43 | 272 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 82 | 219 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 93 | 221 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 26 | 289 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 9 | 304 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 75 | 239 | n/a |
| Prompt | Tier | Tremor | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Intermediate | 0 | 45 | 131 | 207 | 0% |
| weather-dashboard | Beginner | 31 | 0 | 7 | 358 | 100% |
| weather-dashboard | Advanced | 31 | 0 | 4 | 355 | 100% |
| documentation-site | Advanced | 0 | 26 | 68 | 279 | 0% |
| weather-dashboard | Intermediate | 9 | 0 | 31 | 338 | 100% |
| documentation-site | Beginner | 0 | 8 | 274 | 103 | 0% |
| fitness-tracking-app | Advanced | 3 | 0 | 29 | 357 | 100% |
| fitness-tracking-app | Intermediate | 2 | 0 | 14 | 383 | 100% |
| fitness-tracking-app | Beginner | 1 | 0 | 18 | 376 | 100% |
| real-estate-website | Advanced | 1 | 0 | 29 | 364 | 100% |
| real-estate-website | Beginner | 0 | 0 | 27 | 356 | n/a |
| real-estate-website | Intermediate | 0 | 0 | 21 | 373 | n/a |
| saas-application | Intermediate | 0 | 0 | 48 | 351 | n/a |
| saas-application | Beginner | 0 | 0 | 4 | 395 | n/a |
| saas-application | Advanced | 0 | 0 | 83 | 315 | n/a |
