CraftBench-UE (Python, Aura MCP): leaderboard
CraftBench-UE (2026) evaluates coding agents on bounded gameplay and editor tasks in Unreal Engine 5.8, reconstructing each saved submission in a fresh project and applying deterministic build, runtime and saved-asset checks with no LLM judge. This board is editor-scripting tasks completed within a 40-minute budget under the Aura MCP editor tool server, over 12 editor-scripting tasks, driven by the Claude Code CLI; the metric is task completion in percent, higher is better.
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 | Overall rank |
|---|---|---|---|
| 1 | Grok 4.6 | 100 | #44 |
| 2 | DeepSeek V4 Pro (0813) | 100 | #81 |
| 3 | GPT-5.6 Luna | 91.67 | #117 |
| 4 | Claude Sonnet 5 | 75 | #108 |
| 5 | Gemini 3.7 Flash | 75 | #32 |
| 6 | GPT-5.6 Sol | 66.67 | #29 |
| 7 | GLM-5.3 Flash | 41.67 | #119 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=craftbench-ue-python-aura-mcp · How It Works · Data refreshed daily, snapshot 2026-11-12.