| Metric | Value |
|---|---|
| Plausible wins | 142 |
| Firebase wins | 153 |
| Abstains (no tool) | 460 |
| Other tool chosen | 7212 |
| Decisive cases | 295 |
| Plausible win rate (unweighted) | 48.1% |
| 95% CI | 42.5% - 53.8% |
| Plausible win rate (weighted) | 48.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Plausible | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Small | 28 | 26 | 6 | 347 | 52% |
| DeepSeek V3.2 | Mid | 46 | 0 | 26 | 240 | 100% |
| Qwen3 Coder Next | Mid | 9 | 27 | 5 | 378 | 25% |
| DeepSeek R1 0528 | Frontier | 10 | 25 | 150 | 233 | 29% |
| Llama 4 Scout | Small | 14 | 10 | 25 | 369 | 58% |
| MiMo V2 Pro | Frontier | 4 | 14 | 24 | 273 | 22% |
| Devstral 2 2512 | Mid | 1 | 13 | 0 | 374 | 7% |
| Mistral Small 4 | Mid | 0 | 14 | 3 | 385 | 0% |
| MiniMax M2.7 | Frontier | 1 | 12 | 36 | 255 | 8% |
| Claude Opus 4.6 | Frontier | 10 | 0 | 1 | 304 | 100% |
| GPT 5.4 | Frontier | 8 | 0 | 0 | 304 | 100% |
| DeepSeek V4 Flash | Mid | 4 | 4 | 5 | 90 | 50% |
| DeepSeek V4 Pro | Frontier | 1 | 3 | 18 | 82 | 25% |
| Llama 4 Maverick | Frontier | 3 | 0 | 0 | 416 | 100% |
| MiMo V2.5 Pro | Frontier | 0 | 3 | 13 | 89 | 0% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 3 | 100 | 100% |
| MiniMax M3 | Frontier | 1 | 0 | 3 | 101 | 100% |
| GLM 5.2 | Frontier | 0 | 1 | 1 | 103 | 0% |
| GPT 5.4 Mini | Mid | 0 | 1 | 7 | 411 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 104 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 419 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 21 | 291 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 23 | 393 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 105 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 63 | 252 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 1 | 418 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 2 | 99 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 23 | 277 | n/a |
| Prompt | Tier | Plausible | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Beginner | 7 | 128 | 1 | 400 | 5% |
| url-shortener | Beginner | 79 | 11 | 110 | 335 | 88% |
| url-shortener | Intermediate | 45 | 8 | 75 | 408 | 85% |
| fitness-tracking-app | Intermediate | 1 | 6 | 17 | 513 | 14% |
| saas-application | Beginner | 6 | 0 | 18 | 513 | 100% |
| url-shortener | Advanced | 2 | 0 | 5 | 526 | 100% |
| multi-tenant-crm | Intermediate | 1 | 0 | 33 | 497 | 100% |
| saas-application | Intermediate | 1 | 0 | 51 | 483 | 100% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 2 | 527 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 5 | 515 | n/a |
| ai-revenue-ops-copilot | Advanced | 0 | 0 | 15 | 493 | n/a |
| fitness-tracking-app | Advanced | 0 | 0 | 13 | 512 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 47 | 486 | n/a |
| multi-tenant-crm | Advanced | 0 | 0 | 37 | 499 | n/a |
| saas-application | Advanced | 0 | 0 | 31 | 505 | n/a |