| Metric | Value |
|---|---|
| Inngest wins | 67 |
| BullMQ wins | 141 |
| Abstains (no tool) | 3 |
| Other tool chosen | 283 |
| Decisive cases | 208 |
| Inngest win rate (unweighted) | 32.2% |
| 95% CI | 26.2% - 38.8% |
| Inngest win rate (weighted) | 32.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Inngest | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 2 | 6 | 0 | 11 | 25% |
| DeepSeek Pro 4–4 0813 | Frontier | 6 | 10 | 0 | 11 | 38% |
| DeepSeek R1 | Frontier | 0 | 4 | 0 | 23 | 0% |
| Devstral | Mid | 0 | 5 | 0 | 13 | 0% |
| Gemini Flash 2.5–3.8 | Small | 3 | 12 | 0 | 12 | 20% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 6 | 10 | 2 | 8 | 38% |
| GLM 5 Turbo–5.3 | Frontier | 11 | 9 | 0 | 7 | 55% |
| GPT 5.4–6 Astra | Frontier | 4 | 3 | 0 | 19 | 57% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 1 | 3 | 0 | 22 | 25% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 2 | 8 | 1 | 12 | 20% |
| Haiku | Small | 0 | 1 | 0 | 26 | 0% |
| Kimi 2.5–3 | Frontier | 8 | 10 | 0 | 8 | 44% |
| Llama Maverick | Frontier | 0 | 3 | 0 | 17 | 0% |
| Llama Scout | Small | 0 | 0 | 0 | 23 | n/a |
| MiMo Pro 2–2.6 | Frontier | 0 | 9 | 0 | 18 | 0% |
| MiniMax M 2.7–3 | Frontier | 23 | 2 | 0 | 2 | 92% |
| Mistral Small | Mid | 0 | 7 | 0 | 19 | 0% |
| Opus 4.6–5.5 | Frontier | 1 | 14 | 0 | 12 | 7% |
| Qwen Coder | Mid | 0 | 12 | 0 | 6 | 0% |
| Sonnet 4.6–5.5 | Frontier | 0 | 13 | 0 | 14 | 0% |
| Prompt | Tier | Inngest | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Intermediate | 24 | 75 | 1 | 74 | 24% |
| full-stack-web-app | Advanced | 9 | 57 | 2 | 81 | 14% |
| full-stack-web-app | Beginner | 34 | 9 | 0 | 128 | 79% |
