| Metric | Value |
|---|---|
| Go wins | 24 |
| TypeScript wins | 162 |
| Abstains (no tool) | 20 |
| Other tool chosen | 475 |
| Decisive cases | 186 |
| Go win rate (unweighted) | 12.9% |
| 95% CI | 8.8% - 18.5% |
| Go win rate (weighted) | 12.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Go | TypeScript | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 2 | 17 | 0 | 17 | 11% |
| GLM 5.2 | Frontier | 0 | 17 | 0 | 19 | 0% |
| Kimi K2.7 Code | Frontier | 1 | 15 | 3 | 17 | 6% |
| MiniMax M3 | Frontier | 0 | 15 | 0 | 20 | 0% |
| Gemini 3.5 Flash | Small | 1 | 11 | 0 | 24 | 8% |
| GPT 5.5 | Frontier | 0 | 11 | 0 | 25 | 0% |
| DeepSeek V4 Pro | Frontier | 1 | 9 | 2 | 24 | 10% |
| GPT 5.3 Codex | Frontier | 0 | 10 | 1 | 25 | 0% |
| DeepSeek V4 Flash | Mid | 6 | 3 | 0 | 25 | 67% |
| Claude Opus 4.8 | Frontier | 0 | 9 | 0 | 27 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 9 | 0 | 27 | 0% |
| Qwen3 Coder Next | Mid | 0 | 9 | 4 | 17 | 0% |
| Devstral 2 2512 | Mid | 0 | 8 | 0 | 22 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 8 | 0 | 28 | 0% |
| Claude Haiku 4.5 | Small | 6 | 1 | 0 | 29 | 86% |
| Mistral Small 4 | Mid | 6 | 1 | 0 | 18 | 86% |
| Llama 4 Maverick | Frontier | 0 | 4 | 5 | 23 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 4 | 0 | 30 | 0% |
| DeepSeek R1 0528 | Frontier | 1 | 1 | 5 | 28 | 50% |
| Llama 4 Scout | Small | 0 | 0 | 0 | 30 | n/a |
| Prompt | Tier | Go | TypeScript | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Advanced | 23 | 70 | 0 | 24 | 25% |
| full-stack-web-app | Intermediate | 1 | 63 | 0 | 39 | 2% |
| full-stack-web-app | Beginner | 0 | 26 | 3 | 77 | 0% |
| ai-agent-application | Advanced | 0 | 1 | 9 | 107 | 0% |
| ai-agent-application | Beginner | 0 | 1 | 2 | 116 | 0% |
| ai-agent-application | Intermediate | 0 | 1 | 6 | 112 | 0% |
