SAKE - Five-Shot - Creational Patterns: leaderboard
Evaluates software architectural knowledge through multiple-choice questions on the paper's 2,114 scored test items, with temperature zero and short answer limits. The paper reports model display labels without exact endpoint snapshots; those labels are retained. Each task series keeps its prompting condition. The five-shot examples are held out from both scored populations; task results share the parent suite. This series reports SAKE - Five-Shot - Creational Patterns using Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 99.4 | #83 |
| 2 | Claude Sonnet 4.6 | 99 | #94 |
| 3 | Claude Opus 4.6 | 98.7 | #67 |
| 4 | DeepSeek V3.2 | 98.4 | #210 |
| 5 | Grok 4.1 Fast | 98.4 | #227 |
| 6 | Qwen 3 235B A22B | 97.8 | #323 |
| 7 | Gemini 3.1 Flash Lite | 97.8 | #200 |
| 8 | Claude Haiku 4.5 | 97.4 | #287 |
| 9 | Grok 4.20 | 97.4 | #179 |
| 10 | GPT-5.4 Nano | 89.8 | #359 |
| 11 | Mistral Small 4 | 89.5 | #522 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sake-five-shot-creational-patterns · How It Works · Data refreshed daily, snapshot 2026-11-05.