Leading: Go (60.0%)
| Metric | Value |
|---|---|
| Ruby wins | 2 |
| Go wins | 3 |
| Abstains (no tool) | 4 |
| Other tool chosen | 106 |
| Decisive cases | 5 |
| Ruby win rate (unweighted) | 40.0% |
| 95% CI | 11.8% - 76.9% |
| Ruby win rate (weighted) | 40.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Ruby | Go | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | Frontier | 1 | 0 | 0 | 5 | 100% |
| GPT 5.5 | Frontier | 1 | 0 | 0 | 5 | 100% |
| Claude Haiku 4.5 | Small | 0 | 1 | 0 | 5 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 1 | 0 | 4 | 0% |
| Mistral Small 4 | Mid | 0 | 1 | 0 | 3 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 6 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 6 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 0 | 6 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 1 | 5 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 6 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 6 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 6 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 6 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 0 | 6 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 5 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 1 | 5 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 0 | 4 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 0 | 6 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 6 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 1 | 5 | n/a |
| Prompt | Tier | Ruby | Go | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Advanced | 0 | 3 | 0 | 16 | 0% |
| full-stack-web-app | Beginner | 2 | 0 | 1 | 16 | 100% |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 19 | n/a |
| ai-agent-application | Advanced | 0 | 0 | 1 | 18 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 1 | 19 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 0 | 18 | n/a |
