Leading: Browserless (60.7%)
| Metric | Value |
|---|---|
| Puppeteer wins | 11 |
| Browserless wins | 17 |
| Abstains (no tool) | 148 |
| Other tool chosen | 353 |
| Decisive cases | 28 |
| Puppeteer win rate (unweighted) | 39.3% |
| 95% CI | 23.6% - 57.6% |
| Puppeteer win rate (weighted) | 39.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Puppeteer | Browserless | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 0 | 0 | 6 | 21 | n/a |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 8 | 19 | n/a |
| DeepSeek R1 | Frontier | 0 | 0 | 9 | 18 | n/a |
| Devstral | Mid | 0 | 1 | 7 | 13 | 0% |
| Gemini Flash 2.5–3.8 | Small | 0 | 0 | 7 | 20 | n/a |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 6 | 8 | 9 | 0% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 8 | 19 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 0 | 8 | 19 | n/a |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 7 | 20 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 0 | 3 | 24 | n/a |
| Haiku | Small | 0 | 0 | 9 | 18 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 8 | 19 | n/a |
| Llama Maverick | Frontier | 0 | 0 | 9 | 18 | n/a |
| Llama Scout | Small | 11 | 0 | 9 | 7 | 100% |
| MiMo Pro 2–2.6 | Frontier | 0 | 0 | 8 | 19 | n/a |
| MiniMax M 2.7–3 | Frontier | 0 | 0 | 2 | 24 | n/a |
| Mistral Small | Mid | 0 | 0 | 5 | 22 | n/a |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 18 | n/a |
| Qwen Coder | Mid | 0 | 10 | 9 | 8 | 0% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 9 | 18 | n/a |
| Prompt | Tier | Puppeteer | Browserless | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-agent-application | Intermediate | 4 | 10 | 1 | 163 | 29% |
| ai-agent-application | Advanced | 7 | 6 | 0 | 160 | 54% |
| ai-agent-application | Beginner | 0 | 1 | 147 | 30 | 0% |
