WRENCH (Factorio)
Agents build Factorio factories and recover from unannounced disruptions. The evaluator measures how much production the factory retains after a disruption.
On August 10, 2026, Claude Sonnet 5 reached the 1.5 scoring cap on the adaptive and observability tasks. The authors also tested GPT-5.1 and Gemini 2.5 Pro.
- Made by
- WRENCH authors
- Released
- August 2026
- Kind
- Video games
- Level
- University
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Factorio
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Sonnet 5 #35 on the capability index
- Last model added
- June 2026
- Scores refreshed
- November 21st, 2026
Claude Sonnet 5 leads with 1.49
Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. The source reports no overall score, so this is the plain mean of the three published task TR scores. Where a model ran with several settings or harnesses, we keep its best.
Source: Official WRENCH (Factorio) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 5 | 1.49 | Jun 2026 | Official leaderboard | |
| 2 | | 0.81 | Jun 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official WRENCH (Factorio) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Games and long tasks
- ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
- Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games.
Gemini 2.5 Pro 3.90
- MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks.
Seed2.0 Pro 49%
- TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress.
Llama 4 Scout 7.00
- GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
- Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (2 entries).
- Note Models scored Only 2 models we track.
- Pass Newest score The newest is from June 2026, for Claude Sonnet 5.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 5 (#35).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 2 rows for models we track at the last read.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.