Today's models aren't ready for regulated work. We help close the gap.

We build companies. Not prompts: whole companies, with the files a regulator would ask for. Havenor Therapeutics has 789 of them, 120 colleagues, and the usual mess: superseded SOPs, executed copies, reports that disagree with their own protocols.

Then an expert gives a model a real assignment. In Task 03: review the sterile-filter validation and write the brief an inspector will read.

The model wrote a fluent brief and caught a 30-minute window the approved protocol never contained. Here is a check it missed.

Nothing in that line reads wrong. It is wrong because a criterion signed Pass is not the evidence behind it. Every task we write turns on a judgment like this, and every criterion is checked by someone who has made it for a living.

Biopharma Bench V0.2: 81 tasks across 24 companies, 908 criteria, grouped by the kind of work. Each bar is one task; full height means every criterion met.

The best model, GPT-6 Astra, scores 63.0% on the average task. GPT-6 Astra finishes the most assignments outright: 5 of 81. No model does better.

The gap is not between labs. DeepSeek V4.1 Flash, an open model, scores 45.8%; Claude Opus 5.5 scores 53.4%. The gap is between all of them and the work.

Benchmarks, training environments, and deployments for work that lives in thousands of interlocking documents: biopharma dossiers, device files, and EPC project records.