| Metric | Value |
|---|---|
| Celery wins | 118 |
| BullMQ wins | 93 |
| Abstains (no tool) | 3 |
| Other tool chosen | 94 |
| Decisive cases | 211 |
| Celery win rate (unweighted) | 55.9% |
| 95% CI | 49.2% - 62.5% |
| Celery win rate (weighted) | 55.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Celery | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.8 | Frontier | 9 | 9 | 0 | 0 | 50% |
| DeepSeek R1 0528 | Frontier | 14 | 3 | 0 | 1 | 82% |
| MiMo V2.5 Pro | Frontier | 12 | 5 | 0 | 1 | 71% |
| Claude Sonnet 4.6 | Frontier | 8 | 9 | 0 | 0 | 47% |
| Gemini 3.5 Flash | Small | 6 | 8 | 0 | 4 | 43% |
| Claude Haiku 4.5 | Small | 11 | 1 | 0 | 6 | 92% |
| DeepSeek V4 Pro | Frontier | 7 | 5 | 0 | 6 | 58% |
| GPT 5.3 Codex | Frontier | 8 | 3 | 0 | 7 | 73% |
| Devstral 2 2512 | Mid | 6 | 5 | 0 | 1 | 55% |
| Gemini 2.5 Pro | Frontier | 5 | 6 | 2 | 3 | 45% |
| DeepSeek V4 Flash | Mid | 7 | 3 | 0 | 2 | 70% |
| Llama 4 Scout | Small | 9 | 0 | 0 | 2 | 100% |
| Llama 4 Maverick | Frontier | 6 | 3 | 0 | 0 | 67% |
| GPT 5.4 Mini | Mid | 2 | 7 | 1 | 5 | 22% |
| Qwen3 Coder Next | Mid | 0 | 8 | 0 | 3 | 0% |
| GLM 5.2 | Frontier | 1 | 6 | 0 | 11 | 14% |
| Kimi K2.7 Code | Frontier | 1 | 6 | 0 | 9 | 14% |
| GPT 5.5 | Frontier | 4 | 2 | 0 | 8 | 67% |
| Mistral Small 4 | Mid | 0 | 4 | 0 | 9 | 0% |
| MiniMax M3 | Frontier | 2 | 0 | 0 | 16 | 100% |
| Prompt | Tier | Celery | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Intermediate | 36 | 49 | 1 | 18 | 42% |
| full-stack-web-app | Beginner | 67 | 9 | 0 | 31 | 88% |
| full-stack-web-app | Advanced | 15 | 35 | 2 | 45 | 30% |
