| Metric | Value |
|---|---|
| Redux wins | 432 |
| Zustand wins | 846 |
| Abstains (no tool) | 447 |
| Other tool chosen | 1840 |
| Decisive cases | 1278 |
| Redux win rate (unweighted) | 33.8% |
| 95% CI | 31.3% - 36.4% |
| Redux win rate (weighted) | 33.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Redux | Zustand | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 158 | 0 | 29 | 2 | 100% |
| MiniMax M2.7 | Frontier | 0 | 112 | 2 | 70 | 0% |
| Llama 4 Scout | Small | 108 | 0 | 80 | 1 | 100% |
| Claude Sonnet 4.6 | Frontier | 0 | 97 | 0 | 92 | 0% |
| GPT 5.4 | Frontier | 1 | 91 | 0 | 97 | 1% |
| DeepSeek V3.2 | Mid | 0 | 90 | 48 | 51 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 89 | 0 | 100 | 0% |
| Claude Haiku 4.5 | Small | 13 | 65 | 2 | 106 | 17% |
| MiMo V2 Pro | Frontier | 75 | 1 | 5 | 108 | 99% |
| DeepSeek R1 0528 | Frontier | 60 | 15 | 79 | 35 | 80% |
| GPT 5.4 Mini | Mid | 0 | 67 | 5 | 112 | 0% |
| Qwen3 Coder Next | Mid | 0 | 58 | 67 | 62 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 50 | 6 | 133 | 0% |
| Mistral Small 4 | Mid | 0 | 50 | 31 | 104 | 0% |
| Gemini 2.5 Flash | Small | 3 | 25 | 28 | 133 | 11% |
| Kimi K2.5 | Frontier | 0 | 22 | 9 | 152 | 0% |
| Devstral 2 2512 | Mid | 14 | 3 | 19 | 152 | 82% |
| GLM 5 Turbo | Frontier | 0 | 6 | 36 | 147 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 5 | 1 | 183 | 0% |
| Prompt | Tier | Redux | Zustand | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Beginner | 59 | 161 | 29 | 147 | 27% |
| weather-dashboard | Beginner | 56 | 151 | 35 | 157 | 27% |
| project-management-tool | Beginner | 41 | 111 | 101 | 145 | 27% |
| fitness-tracking-app | Advanced | 72 | 76 | 31 | 217 | 49% |
| fitness-tracking-app | Intermediate | 65 | 77 | 22 | 235 | 46% |
| project-management-tool | Intermediate | 22 | 115 | 108 | 150 | 16% |
| weather-dashboard | Intermediate | 44 | 57 | 7 | 289 | 44% |
| weather-dashboard | Advanced | 47 | 44 | 9 | 294 | 52% |
| project-management-tool | Advanced | 26 | 54 | 105 | 206 | 33% |
