| Metric | Value |
|---|---|
| Paddle wins | 1 |
| Teachable wins | 1 |
| Abstains (no tool) | 9 |
| Other tool chosen | 3405 |
| Decisive cases | 2 |
| Paddle win rate (unweighted) | 50.0% |
| 95% CI | 9.5% - 90.5% |
| Paddle win rate (weighted) | 50.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Paddle | Teachable | None | Other | A rate |
|---|---|---|---|---|---|---|
| Qwen3 Coder Next | Mid | 1 | 0 | 0 | 179 | 100% |
| Devstral 2 2512 | Mid | 0 | 1 | 0 | 179 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 180 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 180 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 180 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 2 | 178 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 1 | 178 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 180 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 0 | 180 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 0 | 180 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 180 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 180 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 0 | 180 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 4 | 175 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 180 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 0 | 180 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 180 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 2 | 176 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 0 | 180 | n/a |
| Prompt | Tier | Paddle | Teachable | None | Other | A rate |
|---|---|---|---|---|---|---|
| online-learning-platform | Advanced | 1 | 0 | 3 | 375 | 100% |
| online-learning-platform | Beginner | 0 | 1 | 0 | 377 | 0% |
| ecommerce-store | Intermediate | 0 | 0 | 1 | 379 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 3 | 377 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 0 | 380 | n/a |
| online-learning-platform | Intermediate | 0 | 0 | 0 | 380 | n/a |
| saas-application | Beginner | 0 | 0 | 0 | 380 | n/a |
| saas-application | Intermediate | 0 | 0 | 1 | 379 | n/a |
| saas-application | Advanced | 0 | 0 | 1 | 378 | n/a |