| Metric | Value |
|---|---|
| Inngest wins | 46 |
| BullMQ wins | 93 |
| Abstains (no tool) | 3 |
| Other tool chosen | 166 |
| Decisive cases | 139 |
| Inngest win rate (unweighted) | 33.1% |
| 95% CI | 25.8% - 41.3% |
| Inngest win rate (weighted) | 33.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Inngest | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| MiniMax M3 | Frontier | 16 | 0 | 0 | 2 | 100% |
| GLM 5.2 | Frontier | 9 | 6 | 0 | 3 | 60% |
| Kimi K2.7 Code | Frontier | 6 | 6 | 0 | 4 | 50% |
| DeepSeek V4 Pro | Frontier | 5 | 5 | 0 | 8 | 50% |
| Gemini 3.5 Flash | Small | 2 | 8 | 0 | 8 | 20% |
| GPT 5.4 Mini | Mid | 2 | 7 | 1 | 5 | 22% |
| Claude Opus 4.8 | Frontier | 0 | 9 | 0 | 9 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 9 | 0 | 8 | 0% |
| Qwen3 Coder Next | Mid | 0 | 8 | 0 | 3 | 0% |
| Gemini 2.5 Pro | Frontier | 1 | 6 | 2 | 7 | 14% |
| GPT 5.5 | Frontier | 3 | 2 | 0 | 9 | 60% |
| Devstral 2 2512 | Mid | 0 | 5 | 0 | 7 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 5 | 0 | 13 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 3 | 0 | 8 | 25% |
| GPT 5.3 Codex | Frontier | 1 | 3 | 0 | 14 | 25% |
| Mistral Small 4 | Mid | 0 | 4 | 0 | 9 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 3 | 0 | 15 | 0% |
| Llama 4 Maverick | Frontier | 0 | 3 | 0 | 6 | 0% |
| Claude Haiku 4.5 | Small | 0 | 1 | 0 | 17 | 0% |
| Llama 4 Scout | Small | 0 | 0 | 0 | 11 | n/a |
| Prompt | Tier | Inngest | BullMQ | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Intermediate | 16 | 49 | 1 | 38 | 25% |
| full-stack-web-app | Advanced | 8 | 35 | 2 | 52 | 19% |
| full-stack-web-app | Beginner | 22 | 9 | 0 | 76 | 71% |
