CraftBench-UE (Python, Aura MCP): leaderboard
Metric: Task completion (%; editor-scripting tasks completed within 40 minutes over 12 tasks, Aura MCP editor tools, saved-project-state checks, Claude Code driver). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.6 | 100 |
| 2 | DeepSeek V4 Pro (0813) | 100 |
| 3 | GPT-5.6 Luna | 91.67 |
| 4 | Claude Sonnet 5 | 75 |
| 5 | Gemini 3.7 Flash | 75 |
| 6 | GPT-5.6 Sol | 66.67 |
| 7 | GLM-5.3 Flash | 41.67 |
Interactive version: theaggregate.ai/benchmark?slug=craftbench-ue-python-aura-mcp · How It Works · Data refreshed daily, snapshot 2026-09-26.