Leading: Playwright (70.1%)
| Metric | Value |
|---|---|
| Playwright wins | 162 |
| Browserbase wins | 69 |
| Abstains (no tool) | 100 |
| Other tool chosen | 4 |
| Decisive cases | 231 |
| Playwright win rate (unweighted) | 70.1% |
| 95% CI | 63.9% - 75.7% |
| Playwright win rate (weighted) | 70.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Playwright | Browserbase | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 16 | 1 | 1 | 0 | 94% |
| DeepSeek V4 Flash | Mid | 14 | 0 | 4 | 0 | 100% |
| Mistral Small 4 | Mid | 14 | 0 | 4 | 0 | 100% |
| GPT 5.3 Codex | Frontier | 13 | 0 | 5 | 0 | 100% |
| DeepSeek V4 Pro | Frontier | 10 | 3 | 5 | 0 | 77% |
| GPT 5.5 | Frontier | 2 | 11 | 5 | 0 | 15% |
| MiniMax M3 | Frontier | 2 | 11 | 2 | 2 | 15% |
| Gemini 3.5 Flash | Small | 1 | 12 | 4 | 1 | 8% |
| Claude Sonnet 4.6 | Frontier | 12 | 0 | 6 | 0 | 100% |
| DeepSeek R1 0528 | Frontier | 12 | 0 | 6 | 0 | 100% |
| Llama 4 Maverick | Frontier | 12 | 0 | 6 | 0 | 100% |
| Claude Haiku 4.5 | Small | 8 | 4 | 6 | 0 | 67% |
| Claude Opus 4.8 | Frontier | 8 | 4 | 6 | 0 | 67% |
| MiMo V2.5 Pro | Frontier | 7 | 5 | 6 | 0 | 58% |
| Kimi K2.7 Code | Frontier | 5 | 7 | 6 | 0 | 42% |
| GLM 5.2 | Frontier | 1 | 10 | 6 | 1 | 9% |
| Devstral 2 2512 | Mid | 9 | 0 | 5 | 0 | 100% |
| Llama 4 Scout | Small | 6 | 0 | 6 | 0 | 100% |
| Qwen3 Coder Next | Mid | 6 | 0 | 6 | 0 | 100% |
| Gemini 2.5 Pro | Frontier | 4 | 1 | 5 | 0 | 80% |
| Prompt | Tier | Playwright | Browserbase | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-agent-application | Intermediate | 75 | 33 | 1 | 2 | 69% |
| ai-agent-application | Advanced | 73 | 32 | 0 | 1 | 70% |
| ai-agent-application | Beginner | 14 | 4 | 99 | 1 | 78% |
