FactoryBench (Forgis Labs)
Models interpret sensor readings from industrial robot arms and predict how the machines respond to changes. They also recommend actions when the readings indicate a fault.
The authors compare six language models. Programs grade structured answers, and model judges grade written recommendations. The project page reports each reasoning level separately.
- Made by
- Forgis Labs
- Released
- May 2026
- Kind
- Other professions
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- In and out
- Text, Time series → Text
- Interaction
- Single turn
- Items from
- Another benchmark, Generated, Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Sonnet 4.6 #57 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
Claude Sonnet 4.6 leads with 36% among models released by February 2026 Claude Sonnet 4.6 leads with 36% among models released by February 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Claude Sonnet 4.6 Zero-shot 36%
- 2 Qwen3-235B Zero-shot 29.9%
- 3 GPT-5.1 Zero-shot 27.6%
- 4
Mistral Large 3 Zero-shot 27%
- 5
DeepSeek-V3.2 Zero-shot 22.6%
- 6
Qwen3-4B Zero-shot 20.3%
Source: Official FactoryBench (Forgis Labs) leaderboard
- 1 Claude Sonnet 4.6 Zero-shot 36%
- 2 GPT-5.1 Zero-shot 27.6%
- 3
Mistral Large 3 Zero-shot 27%
- 4
DeepSeek-V3.2 Zero-shot 22.6%
- 5
Qwen3-4B Zero-shot 20.3%
Source: Official FactoryBench (Forgis Labs) leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 36% | Zero-shot | Feb 2026 | Official leaderboard |
| 2 | Qwen3-235B | 29.9% | Zero-shot | Official leaderboard | |
| 3 | GPT-5.1 | 27.6% | Zero-shot | Nov 2025 | Official leaderboard |
| 4 | | 27% | Zero-shot | Dec 2025 | Official leaderboard |
| 5 | | 22.6% | Zero-shot | Dec 2025 | Official leaderboard |
| 6 | | 20.3% | Zero-shot | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 36% | Zero-shot | Feb 2026 | Official leaderboard |
| 2 | GPT-5.1 | 27.6% | Zero-shot | Nov 2025 | Official leaderboard |
| 3 | | 27% | Zero-shot | Dec 2025 | Official leaderboard |
| 4 | | 22.6% | Zero-shot | Dec 2025 | Official leaderboard |
| 5 | | 20.3% | Zero-shot | Apr 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as L1 State, L2 Intervention and L3 Counterfactual. Claude Sonnet 4.6 leads 3 of them, and GPT-5.1 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
L1 State
5 models we track have a score here.
- 1 Claude Sonnet 4.6 46.8%
- 2
Mistral Large 3 ↑1 34.6%
- 3 GPT-5.1 ↓1 30.9%
- 4
DeepSeek-V3.2 25%
- 5
Qwen3-4B 21.8%
L2 Intervention
5 models we track have a score here.
- 1 Claude Sonnet 4.6 47.1%
- 2
Mistral Large 3 ↑1 31.7%
- 3 GPT-5.1 ↓1 30%
- 4
DeepSeek-V3.2 29.1%
- 5
Qwen3-4B 27.5%
L3 Counterfactual
5 models we track have a score here.
- 1 Claude Sonnet 4.6 45.9%
- 2
Mistral Large 3 ↑1 36.3%
- 3 GPT-5.1 ↓1 31.7%
- 4
Qwen3-4B ↑1 28.8%
- 5
DeepSeek-V3.2 ↓1 28.5%
L4 Decision
5 models we track have a score here.
- 1 GPT-5.1 ↑1 17.7%
- 2
DeepSeek-V3.2 ↑2 7.60%
- 3
Mistral Large 3 5.40%
- 4 Claude Sonnet 4.6 ↓3 4.30%
- 5
Qwen3-4B 2.90%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official FactoryBench (Forgis Labs) 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 FactoryBench (Forgis Labs) 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 Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Claude Sonnet 4.6. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (6 entries).
- Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 9 months ago, in February 2026, for Claude Sonnet 4.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 4.6 (#57).
- Pass Headroom The best is 36%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on forgis.com: 5 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 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.