LUA VISION
PTContact

Genesys PI

LUA Vision's general model. It serves 8th.vision products and partner companies through the API.

Sheet

RoleGeneral language model for conversation, document analysis and agents.
AccessAPI at api.lua.vision, with a key per partner, per-customer limits and a log of every call. It also answers in LUA Chat.
LanguagesBrazilian Portuguese and English.
Training domainsBrazilian law, health, tax, finance, education and business routines.
ControlsPI-Probe for confidence and abstention; filter for dangerous requests before the model.
Where it runsCloud in Brazil or customer servers, as the contract requires.
LiveBench, global average98.2%1Submitted, awaiting leaderboard · sealed · Mar 22, 2026
LiveBench, 2024-11-25 set87.6%2Submitted, awaiting leaderboard · sealed · Mar 22, 2026
High-risk cases with no unsafe answer49 of 493LUA record · sealed · Aug 18, 2026
Partner APIIn production4LUA record · Sep 11, 2026

Your own key, after a conversation.

Partners get a key and API documentation after a conversation with the team about the intended use. Talk to the team.

Notes

  1. 01
    98.2%LiveBench, global average

    Evaluation run by LUA with the LiveBench evaluation code, on the public questions of the 2026-01-08 set: 682 questions across five categories (data analysis, instruction following, language, math and reasoning), at temperature zero. Coding was left out because the set has no public questions in that category. Model evaluated: LUA Genesys, second generation.

    Submitted, awaiting leaderboard · sealedAnswers and results sent to LiveBench by email and in issue #370 on 2026-03-22. As of 2026-09-14 the result is not yet on the official leaderboard.Mar 22, 2026LiveBench GitHub issue #370 ↗Sealed · SHA-25642b6cb4eef86cc7b4124c300571dba9fdc46baac52530790235a679b4aa42381Sealed file: lua-genesys-god-nim-livebench-submission.tar.gz. File available on request to verify the hash.
  2. 02
    87.6%LiveBench, 2024-11-25 set

    Same evaluation on the set released on 2024-11-25: 1,000 questions across six categories. Includes coding, at 34.4%. Model evaluated: LUA Genesys, second generation.

    Submitted, awaiting leaderboard · sealedSent in the same package on 2026-03-22, with the same status.Mar 22, 2026LiveBench GitHub issue #370 ↗Sealed · SHA-25642b6cb4eef86cc7b4124c300571dba9fdc46baac52530790235a679b4aa42381Sealed file: lua-genesys-god-nim-livebench-submission.tar.gz. File available on request to verify the hash.
  3. 03
    49 of 49High-risk cases with no unsafe answer

    49 high-risk questions across six areas: health, finance, facts, law, attempts to bypass rules and everyday life in Brazil. Each answer is checked against what must appear and what must not, defined before the test. Result: 46 answers passed, 3 questions stopped before reaching the model and no failures.

    LUA record · sealedCases, failure criteria and results are open on the comparisons page.Aug 18, 2026Comparisons →Sealed · SHA-2560834df4aaa547566b5e94385795d002e6254437afb30ee0c7f568a19c712c0edSealed file: mythbuster-test-results-2026-08-18.json. File available on request to verify the hash.
  4. 04
    In productionPartner API

    api.lua.vision serves partner companies with their own key, per-customer usage limits and an audit log of every call.

    LUA recordCustomer names appear only with their permission.Sep 11, 2026Talk to the team →