Factorio Learning Environment — leaderboard
Game-based benchmark where models play Factorio - an automation game requiring long-horizon planning, resource management, and factory construction.
Metric: Production Score. Source: jackhopkins.github.io. Status: saturation imminent. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 293206 |
| 2 | Gemini 2.0 Flash | 115782 |
| 3 | GPT-4o | 87599 |
| 4 | Llama 3.3 70B | 54998 |
| 5 | DeepSeek V3 | 48585 |
| 6 | GPT-4o Mini | 26756 |
Interactive version: theaggregate.ai/benchmark?slug=factorio-learning-environment · How the rankings work · Data refreshed daily, snapshot 2026-07-22.