New Report: Leading AI Models Score at Most 52% on Industrial Parts Questions, Reshape Automation Finds

SAN FRANCISCO--(BUSINESS WIRE)--Oct 7, 2026--

A customer asks their distributor whether a Siemens communication module, part number 3RW5950-0CH00, works with a 3RW52 soft starter, and the distributor turns to AI to find out. Claude, with web search turned on, said yes all three times it was asked. The verified answer is no. The module belongs with the 3RW55 series, and an order placed on that answer ships a part that doesn’t fit the equipment it was bought for.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261006085279/en/

That question is one of 100 in the Industrial AI Accuracy Index 2026, published today by Reshape Automation, covering 14 manufacturer catalogs including Siemens, Festo, Rittal and ATI Industrial Automation.

What the models got wrong

Why the models get parts questions wrong

“The AI products on the market today are mostly a general-purpose model with search or a document store bolted on, and they’re very good at a lot of work,” said Juan Aparicio, CEO and co-founder of Reshape Automation. “Parts questions are different. The answer is usually a relationship between three or four facts that live in different places, like a catalog, a datasheet or a cross-reference table, and some of it was never written down at all. If the model has to rebuild that relationship every time someone asks, it’ll sometimes get it right and sometimes not, and it’ll sound equally sure both times.”

“Distributors are where these questions land,” Aparicio said. “A customer asks whether a part fits, someone on the inside sales team has a few minutes to answer, and one wrong digit ships the wrong part. A tool that’s right half the time doesn’t save that person any work, because they still have to check every answer.”

What ReshapeX does differently

ReshapeX is Reshape Automation’s family of AI agents for the technical and commercial work behind industrial sales and support: customer service, application engineering, inside sales and field maintenance. The agents select and size products, build valid part numbers from specs, find replacements and accessories, and cross-reference and price a bill of materials hundreds of lines long. They quote RFQs, answer “where’s my order?”, walk a technician through a fix, and show a sales rep what an account bought, stopped buying and could buy next.

They work inside the ERP and CRM and wherever customers and staff already are: website chat, Outlook, Microsoft Teams, WhatsApp and voice. Reshape customers report 60% to 90% time savings in technical support, customer service and inside sales, and an 18.6% increase in average order value.

The agents leverage leading AI models, such as GPT and Claude, and Reshape builds the harness around the model: the knowledge it answers from, the tools it can call, and the checks an answer passes before a customer sees it.

That knowledge is assembled once, before anyone asks. For each manufacturer, Reshape pulls the catalog, datasheets, cross-reference data and the rules the brand’s engineers know into one knowledge graph that stores the relationships: what fits what, how a configured part number is built, what replaced a discontinued part. Every fact carries its source, and engineers review the graph before any agent uses it. The agents still search the web or check live stock when that’s the right source. Ask the same question twice and you get the same answer.

item, the German maker of aluminum building-kit systems, runs a ReshapeX agent on its U.S. and Mexico websites in English and Spanish. The agent answers from item’s own product data across more than 4,500 mutually compatible components, and when a question goes past what it can verify, it hands the customer to an item Expert with the whole conversation attached.

“Most AI on a website waits for you to ask and forgets you the moment you leave. The item agent is part of item’s journey, not a box bolted onto it,” said Germain Dufossé, CEO of item America.

How the test was run

Reshape’s engineers wrote up the 100 questions from what customers ask the distributors and OEMs Reshape works with, and no third party reviewed them. The answer key comes from ReshapeX’s own answers, verified against manufacturer documentation, so ReshapeX is not scored on equal terms with the models it tested. Every question is published in the report so anyone can rerun the test.

Each model ran through its provider’s API with a pinned model ID (gpt-6-astra, claude-fable-5-1, gemini-3.8-flash): 1,500 calls on September 24, 2026. Gemini ran without web search because its provider’s terms require written permission to benchmark it with grounding. A model drafted each grade and Reshape’s engineers made the final call. The report lists 13 limitations.

The report prints all 100 questions and a SHA-256 fingerprint of the answer key. The key itself is withheld to keep the questions usable as a test and is available on request. Download the report at https://www.reshapex.com/iaai2026.

Trademarks

GPT-6 Astra, Claude, Gemini, Siemens, Festo, Rittal, ATI Industrial Automation and item are trademarks of their respective owners. None of them commissioned, reviewed, sponsored or endorsed this evaluation.

Download images: Here

Reshape Automation

Reshape Automation, Inc. builds AI agents that take on the tedious technical and commercial work of industrial sales and support. Its ReshapeX agents select and configure products, cross-reference parts and full bills of materials, prepare quotes, track orders, guide field troubleshooting and surface account insights for distributors, OEMs, system integrators and manufacturers. They work inside the customer’s ERP and CRM and run on websites, Outlook, Microsoft Teams, WhatsApp and voice. Each agent answers from a knowledge graph built from the manufacturer’s own catalogs and engineering knowledge, kept current as catalogs change, and Reshape’s forward-deployed engineers take every deployment into production alongside the customer. More at www.reshapex.com.

One of the 100 industrial parts questions in Reshape Automation’s report: a customer asks a distributor whether a Siemens module works with their soft starter. A general-purpose AI model says yes, missing that the two belong to different product series. ReshapeX answers from the manufacturer’s own documentation, says no and names the right series before a wrong part gets quoted or ordered.

STOCKHOLM (AP) — Scientists Henri B. Kagan and Kenso Soai won the Nobel Prize in chemistry Wednesday for untangling mysterious mirror images in molecules, a discovery that has been used to develop countless drugs and transformed modern medicine.

Many molecules come in versions that look alike but are not exactly identical, like right and left hands. One mirror image of the chemical carvone smells like mint, for example, while the other has a whiff of caraway, a spice often used in rye bread.

Even life itself prefers one mirror image over the other. DNA twists to the right, and the proteins in human bodies are made of mostly left-handed building blocks.

Versions of the same molecule can behave differently when interacting with other chemicals. When designing drugs to treat diseases, scientists want to be choosy about which mirror image they get. They want the version of a molecule to treat a cold, not one that will make the sniffles worse.

Kagan, who is from France, and Soai, from Japan, found ways to make chemistry pick a side, designing and manipulating reactions to produce the desired mirror image.

“This is probably the coolest experiment in organic chemistry,” said Peter Somfai, a member of the Nobel Committee for Chemistry. “Taken together, the groundbreaking discoveries by Henri Kagan and Kenso Soai have reshaped our understanding of molecular chirality,” a term that comes from the Greek word for “hand.”

Scientists paid tribute to Kagan and Soai's work, which the Nobel committee described as a feat never previously achieved by anyone “other than life itself.”

“It might be difficult to say that this drug, or that drug, was developed using this,” Somfai said. “I would say all of them, because we use this as a tool, we use this as an understanding, how to develop catalysts, how they function.”

In the 1980s, Kagan’s work showed there might be a way to design reactions to produce one form of a molecule over the other. Years later, Soai perfected the process. He created the first-ever chemical reaction to efficiently produce only one of a molecule’s mirror images, in what’s now known as the Soai reaction.

“The medicines we have today would not be possible without this chemistry,” said Rigoberto Hernandez, president of the American Chemical Society.

Kagan, 95, is affiliated with the Université Paris-Sud in Orsay, France. Soai, 76, is affiliated with the Tokyo University of Science.

The French Academy of Sciences, of which Kagan is a member, congratulated the two scientists and expressed its pride in the prize.

Neither the Université Paris-Sud nor the Tokyo University of Science immediately responded to requests for comment from The Associated Press.

“I’m very excited to receive the very nice news,” Soai told the committee and journalists by phone. “Of course this is one of the most exciting days in my life.”

He said he was shopping near his home when he was reached by the Nobel committee.

The Royal Swedish Academy of Sciences announced the winner in Stockholm.

Last year, three scientists won the chemistry Nobel for their development of new molecular structures that can trap vast quantities of gas inside, laying the groundwork to potentially suck greenhouse gases out of the atmosphere or harvest moisture from desert environments.

This year's prizes began with the Nobel for medicine, awarded Monday to three scientists whose work led to a tool that uses light to help unravel how the brain works. The physics award Tuesday recognized a scientist's efforts to demystify a rare group of neutrinos.

The literature prize is set to be awarded Thursday. After Friday’s peace prize is awarded, the Nobel Memorial Prize in Economic Sciences will be announced Monday.

The prize money this year is 12 million Swedish kronor (about $1.2 million), whether for an individual, a small group of laureates or an organization.

This story has been corrected to clarify that Kagan, not Soai, is 95.

Ramakrishnan reported from New York. Dazio reported from Berlin. Associated Press journalists Alexa St. John in Detroit, Catherine Gaschka in Paris and Mari Yamaguchi in Tokyo contributed to this report.

AP Nobel Prizes: https://apnews.com/hub/nobel-prizes

Japanese chemist Kenso Soai, who won the 2026 Nobel Prize in Chemistry, leaves home for a press conference, in Shiki, Saitama prefecture, Wednesday, Oct. 7, 2026. (Kyodo News via AP)

Japanese scientist Kenso Soai, winner of the 2026 Nobel Prize in Chemistry, leaves home for a press conference, in Shiki, Saitama prefecture, Wednesday, Oct. 7, 2026. (Kyodo News via AP)

Portraits of Henri Kagan and Kenso Soai are shown on the screen as they are awarded the 2026 Nobel Prize in Chemistry, at the Royal Swedish Academy of Sciences in Stockholm, Sweden, on Oct. 7, 2026. Photo: (Fredrik Sandberg/TT News Agency via AP)

Portraits of Henri Kagan and Kenso Soai are shown on the screen as they are awarded the 2026 Nobel Prize in Chemistry, at the Royal Swedish Academy of Sciences in Stockholm, Sweden, on Oct. 7, 2026. Photo: (Fredrik Sandberg/TT News Agency via AP)

FILE - A close-up view of a Nobel Prize medal at the National Institutes of Health (NIH) in Bethesda, Md., Dec. 8, 2020. (AP Photo/Jacquelyn Martin, File)