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

#ModelScore
1Grok 4.6100
2DeepSeek V4 Pro (0813)100
3GPT-5.6 Luna91.67
4Claude Sonnet 575
5Gemini 3.7 Flash75
6GPT-5.6 Sol66.67
7GLM-5.3 Flash41.67

Interactive version: theaggregate.ai/benchmark?slug=craftbench-ue-python-aura-mcp · How It Works · Data refreshed daily, snapshot 2026-09-26.