FactoryBench: leaderboard
We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs are organized along four causal levels (state, intervention, counterfactual, decision) instantiating Pearl's ladder of causation, and span five answer formats: four structured formats are scored deterministically and free-form answers are scored by
Metric: Overall Score (self-reported). Source: benchmarklist.com. Saturation forecast: Around March 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 20.6 | #135 |
| 2 | Mistral Large 3 | 17.9 | #401 |
| 3 | DeepSeek V3.1 | 17.1 | #264 |
| 4 | Claude Haiku 4.5 | 12.8 | #280 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=factorybench · How It Works · Data refreshed daily, snapshot 2026-10-20.