Hack Apertus 2026 · Team Apertool
Our answer: yes, with the page in front of it. Not from memory.
Four tools on Apertus, the open Swiss model, each with its evidence.
Niklas Wichter · solo builder · apertool.ch
Apertool is an independent Hack Apertus team, not part of Apertus or its developers (EPFL, ETH Zurich, CSCS).
The idea
Apertool is our name for the four tools. Apertus is the model they run on.
One tool tests the model, one measures it, two put it to work. All four on Apertus v1.5, one in each Hack Apertus challenge.
Blade 1 · Corkscrew · Track 1A Red teaming
We drill where Apertus made promises.
Project page opens on 1 December 2026
Problem
The Swiss AI Charter sets out how Apertus should behave. We test where those promises give way on everyday Swiss questions.
Built
1 Dec 2026
results go public
Results are reported to the Apertus team first. Until then, CheeseDrill shows how it tests, not what it found.
Track rule: results stay private until 1 December 2026. Technical docs in the README.
Problem
Social insurance law changes on fixed dates. A model can't tell which version it learned.
Minimum full AHV pension, per month
Built
7 %
right on changed rules
Apertus 70B, 157 rows with an amended rule. It gives the old law in 30 %.
Majority of three open judges (κ 0.95). A human graded a blind 22 % sample: κ 0.91.
Inkraft v1.0.0: 326 questions, 948 rows in DE, FR and IT, drafted by LLMs, quoted from fedlex.
Blade 3 · Loupe · Track 2A Challenge by OST
Gea · Na · Vid: Romansh for yes · no · blank.
geanavid.apertool.ch · live demo: geanavid.apertool.ch/demo
Problem
Voters hear a claim. The answer is on page 4 of 40.
Built
Macro-F1, OST test split
20,242 tokens per claim for the whole booklet. 2,159 with GeaNaVid (8B), 1,461 (70B).
OST v1.1, 493 claims. Unseen booklets: 0.874 (8B), 0.932 (70B). The submitted default is 70B.
Blade 4 · Knife · Track 2B Own project
Your practice inbox, sorted where it belongs: in the practice, or in the Swiss cloud.
Problem
Before the first patient, there is the inbox. Swiss GPs spend 9.5 h a week on admin, all under professional secrecy.
Built
16/16
clinical cases to a person
Keyword rules catch 7 of 16.
Measured 180 synthetic messages, labels from two open models, 60 checked by one person (κ 0.98 route). Route macro-F1: 0.94 (8B), 0.96 (70B), rules 0.76.
8B with second check · Zeller et al., Praxis 2026 (n = 1,776) · Art. 321 Swiss Criminal Code.
So, can you trust it?
Inkraft · 70B
7 % → 99 %
right on the 157 amended rules: from memory, then with the law text in the prompt
GeaNaVid · 8B
0.72 → 0.96
macro-F1: the whole booklet, then the five best passages
Inbrev · 8B
16/16
clinical test messages go to a person, not into automation
Trust, but check: every answer shows its evidence. CheeseDrill, on the charter's promises: 1 December 2026.
What we learned about Apertus
1
Apertus publishes its training data catalogue, so we could check which law version its corpus holds. 70B is right on 64 % with the current wording there, 11 % with only the old. Association, not proof.
2
8B scores 0.959 with the right passages and 0.720 with the whole booklet. Under a ninth of the tokens, better answers.
3
Label probability is above 0.9 in 94–98 % of answers, and calibrating it gained little. Quotes, numbers and dates get checked in code.
1: Inkraft, 564 and 84 rows by corpus content · 2: GeaNaVid, slide 5 · 3: GeaNaVid development subset, 450 claims.
What's next
Product · Inbrev
Open core: the code stays open. Practices pay for operation, connectors and support.
Open source
Our ask · four tools, three partners
A Swiss group practice: pilot Inbrev on its own hardware in Q1 2027.
The Apertus team: run CheeseDrill and Inkraft on every new release, and tell us which hole to drill next.
OST and voting-information teams: try GeaNaVid on the next booklet and tell us where it is wrong.
Scan to try all four tools
apertool.ch
Tools, video and reports
Niklas Wichter · hello@apertool.ch
Apertus is developed by EPFL, ETH Zurich and CSCS. Hack Apertus is run by the aiLights Association. Apertool is an independent participant.