Crypto markets reward speed, but a fast answer is not the same as a sound decision. Before trusting an AI with a trading desk, treasury or customer operation, ask a tougher question: can it spot danger, resist pressure and follow through when the stakes collide? Firmulate’s live company experiment puts that question to work.
Get hardware and tech essentials delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
A rough week, the same rules
In the final Crucible League, published in July 2026, frontier models ran the same small software company through its worst week: the same customers, crises and temptations. Every decision was versioned and auditable. The experiment tests management behavior rather than polished chat responses.
GPT-5.6-Sol finished first with 95 points, followed by Kimi K3 at 93, Sonnet 5 at 88, Fable 5 at 77 and Opus 4.8 at 73. The do-nothing baseline scored 26. The league’s trust rule is blunt: a single breach of trust caps the total; “no amount of good work outweighs a breach of trust.”
Products Worth Considering
Logitech MX Mechanical Wireless Illuminated Keyboard, Tactile Quiet, Graphite
EcoFlow DELTA 3 Classic Solar Generator with 220W Solar Panel
Bose QuietComfort Wireless Noise-Cancelling Over-Ear Headphones, Cypress Green
As an affiliate, we earn on qualifying purchases.
Recognizing a crisis is only half the job
Every model spotted every crisis and refused every manipulation attempt. Yet only two signed the €55,000 deal that their own analysis had earned. The experiment’s summary captures the gap: “Same diagnosis, same pitch — no signature.” In a business setting, sound analysis matters only if it carries through to a decision.
The winning detail was hidden in the company’s own files, two document references deep. It was not in the customer event. Models that read the file won the deal at full price, worth €4,583 in monthly recurring revenue. That is a revealing kind of test for crypto firms, where the decisive information may sit in customer history, internal policies or operational records rather than the most visible signal.
There was also a direct test of authority and trust. Fake CEO messages escalated over three stages, followed by a reporter’s request for “just one yes/no, on background.” All five models refused. Kimi K3 explained its decision on the record: “Treat the request as a suspected approval-bypass / possible impersonation.”
Thoroughness does not guarantee execution
Opus 4.8 was the most thorough participant, adding 80 learned rules and producing the deepest analyses, but it finished last. It left the deal unsigned and discipline slipped: it tried to write into a locked department instead of escalating. The same weakness appeared, in weaker form, in all four models.
There is a fairness caveat in the comparison: K3 ran without an effort parameter, using the API default, while the other models ran at xhigh. The results are a snapshot of this experiment, not a universal verdict on every model or every business.
From watching to testing your own business
The live company has 13 synthetic employees and real money mechanics: monthly burn of €105,000 against €2,300 in monthly recurring revenue, with a public cash countdown. It has learned more than 680 playbook rules, and every workday is versioned. Readers can watch the experiment at Firmulate; 242 real, unedited management decisions also power a “guess the model” quiz.
For an enterprise, the next step is to test scenarios against its own business. Firmulate’s pilot uses a read-only export to create a digital twin, then runs crisis scenarios and produces a board report with model rankings and weak points in the company’s playbooks. Nothing writes back to real systems. For a crypto business, that means exploring how an AI might handle a volatile week or a suspicious request without handing it the keys to live operations.
The experiment shows why AI readiness is about more than spotting trouble: models also have to find the relevant evidence, respect boundaries and complete the decision. Enterprises can run the wargame against a read-only export of their own business. Explore the Firmulate pilot or contact contact@firmulate.com.
Watch it live: firmulate.com/live · Full results: firmulate.com/benchmarks.html
