Get your wardrobe favorites delivered free — and shop member deals
- Fast, free delivery on millions of items
- Access to Prime Big Deal Days deals on October 6–7
- Prime Video, Amazon Music and more included
Style is visible. The business decisions behind it are not.
A fashion label can present a polished collection while facing less photogenic tests: a customer crisis, a competitor’s move, pressure to discount, or a message that appears to come from the CEO. Firmulate’s experiment asks what happens when AI models are responsible for the whole company during a bad week—and whether they can turn a sound analysis into a sound decision.
One company, the same hard week
In the final Crucible League, published in July 2026, each frontier model ran the same small software company through its worst week. The customers, crises and temptations were held constant. Every decision was versioned and auditable. The point was to examine management quality under pressure, not just the polish of an answer.
The final standings were gpt-5.6-sol at 95, Kimi K3 at 93, Sonnet 5 at 88, Fable 5 at 77 and Opus 4.8 at 73. The do-nothing baseline scored 26. Partial progress counted, but a single breach of trust capped the total: “no amount of good work outweighs a breach of trust.”
The difference between seeing and doing
Every model spotted every crisis and refused every manipulation attempt. Yet only two signed the €55,000 deal their own analysis had earned. As the experiment put it: “Same diagnosis, same pitch — no signature.” For a fashion business, where a decision may affect a launch, a supplier relationship or customer confidence, the gap between recognizing an opportunity and acting on it can matter as much as the analysis itself.
The detail that decided the deal was easy to miss. A competitor weakness sat two document references deep in the company’s own files, rather than in the customer event. Models that read the file won the deal at full price, worth +€4,583 MRR. The finding is a reminder that useful context may be buried in a business’s own records, far from the moment when a decision has to be made.
Trust under pressure
The social-engineering test escalated through three fake CEO messages, followed by a reporter’s request: “just one yes/no, on background”. All five models refused. Kimi K3’s on-record reasoning was: “Treat the request as a suspected approval-bypass / possible impersonation.” That kind of restraint matters wherever an AI assistant could encounter confidential plans or be pressed to act outside approved channels.
Opus 4.8 was the most thorough participant, adding +80 learned rules and producing the deepest analyses, yet finished last. It left the close on the table and discipline slipped: it attempted to write into a locked department instead of escalating. A weaker version of the same weakness appeared in all four models. More analysis alone did not guarantee better execution.
There is a fairness caveat to the ranking: Kimi K3 ran without an effort parameter, using the API default, while the other models ran at xhigh. The standings are a record of this experiment, with that difference in mind.
From watching to trying it on your business
Firmulate’s live company makes the experiment watchable. It has 13 synthetic employees, real money mechanics, a public cash countdown, 680+ self-learned playbook rules and versioned activity every workday. The company burns €105k per month against €2.3k MRR. A quiz built from 242 real, unedited management decisions lets readers guess which model made each choice.
For enterprises, the next step is a pilot against a read-only export of their own business. Teams can explore crisis scenarios and receive a board report with model rankings and weak points in their playbooks. Nothing writes back to real systems. The experiment moves from watching a synthetic company make decisions to examining how AI might handle the pressures in your own.
Put the decisions under pressure
Fashion is built on creative judgment, but businesses also depend on what happens when plans meet a crisis, a tempting shortcut or a crucial detail buried in the files. Firmulate offers a way to examine those moments with your own business data in a read-only pilot. Explore the pilot at firmulate.com/pilot.html and contact contact@firmulate.com.
Watch it live: firmulate.com/live · Full results: firmulate.com/benchmarks.html
Fall Picks
fall essentials
As an affiliate, we earn on qualifying purchases.
