01 / Reasoning
Long chains without drift.
Llana sustains multi-step arguments over thousands of tokens, re-reading its own premises when it needs to.
● Llana 3.2 · Lansert mars 2026Volum II · Utgave 07
En modell som tenker, tålmodig, i offentligheten.
Llana er Kapllans flaggskip innen resonnering — bygget for langhorisontproblemer der formen på et godt svar ikke er åpenbar. Den leser nøye, viser fremgangsmåten sin og foretrekker å ha rett fremfor å være rask.
Du
Hvorfor flyter is på vann?
Llana
De fleste faste stoffer synker i sin egen væske fordi frysing pakker molekylene tettere sammen. Vann er uvanlig: når det kjøles under 4°C, tvinger hydrogenbindinger molekylene inn i et åpent heksagonalt gitter som tar mer plass, ikke mindre. Is er omtrent 9% mindre tett enn flytende vann — så den flyter. En liten kuriositet med store følger: innsjøer fryser fra toppen og nedover, og livet overlever vinteren under isen.
§ I — Evner
Bygget for problemer som ikke får plass på én skjerm.
02 / Code
Reads codebases like prose.
128K context with structural awareness — call graphs, test intent, the difference between a bug and a choice.
03 / Research
Cites what it doesn't know.
Calibrated uncertainty — Llana will decline, hedge, or ask a clarifying question before it invents an answer.
04 / Agents
Plans. Executes. Reports back.
A tool-use interface that treats every action as revocable — Llana narrates its intent before it takes one.
05 / Vision
Describes what it sees.
Charts, diagrams, scanned pages, handwritten notes — Llana reads images with the same care it brings to text.
06 / Safety
Refuses with reasons.
Every refusal comes with a justification you can argue with — not a flat wall. Transparency is a design goal, not a patch.
§ II — Ytelse
På testene vi stoler på, og de vi ikke stoler på.
| Benchmark | What it measures | Llana 3.2 | Prior SOTA |
|---|---|---|---|
| ▸MMLU-Pro | Multi-discipline reasoning | 84.1 | 81.3 |
| ▸GPQA-Diamond | Graduate science Q&A | 71.8 | 68.0 |
| ▸SWE-bench Verified | Real-world coding tasks | 62.4 | 58.9 |
| HumanEval | Code synthesis | 94.7 | 94.2 |
| ▸MATH-500 | Competition mathematics | 88.5 | 85.1 |
| AIME 2025 | Olympiad-level problems | 54.2 | 52.0 |
"Vi vil ikke ha en modell som snakker selvsikkert om alt. Vi vil ha en som kjenner formen på sin egen uvitenhet."— Fra den tekniske rapporten til Llana 3
§ III — Forskning
Åpent publisert. Replisert ute i verden.
26 Mar 2026
Calibrated refusal: learning when to not answer
A. Berisha · L. Mora · H. Tanaka · et al.
Pre-print
→
18 Feb 2026
Deliberation as inference: scaling thought at test time
M. Oduya · S. Whitlock · R. Kaur
NeurIPS '26
→
07 Jan 2026
The Llana 3 technical report
Kapllan Research
Report
→
22 Nov 2025
Interpretability without the spotlight effect
J. Pell · N. Moreau · D. Orlov
ICLR '26
→
§ IV — Slik bygger vi
Tre arbeidsprinsipper. Alle forhandlingsbare.
Principle 01
Slow beats showy.
We release models when their behavior is understood, not when a demo looks clean. We would rather publish a late, calibrated model than an early, charismatic one.
Principle 02
Write it down.
Every capability claim is tied to a public evaluation, a dataset, or a paper. If we cannot describe how we measured it, we do not ship it.
Principle 03
Refuse the spectacle.
Research that doesn't reduce to a screenshot is still research. A good question is a legitimate deliverable. We pay for depth.
Arbeid med Llana.
Gratis under offentlig beta. API-tilgang for forskere og utviklere. Bedriftspiloter på forespørsel.