Describe a decision once, as a few typed questions. Amos reads each case, text, JSON or a photo, and answers every question with a probability. It writes no text, so an answer comes back in about a third of a second.
Below, the large model reads six cases, five of them with a photo. Pull a sentence or the photo out and the answers settle to what it said without it. Every number and box is a real answer, recorded through the public API.
Where it stands. On the Decision Index vision board, 55 models scored half on public benchmarks and half on private images never published, Large is second with a Full score of 72.4, 0.1 behind first (edition 0.4.1, 22 October 2026). On the main Decision Index, 226 models, it scores 64.8, against 71.5 for the leader. It leads three other public benchmarks. On Decision Bench, 1,071 real records with their source's own answers, it gets the most right. On typed decisions with each question's priors fitted on the test's own train split, as Decider 1 also reports, it scores 80.3%, the highest fitted score we know of. On JevBench hard it leads Jev by ten points. Ours were picked on our own held-out data. Every model's full results, wins and losses, are on its page.
Rivals as the leaderboard lists them unless noted; ours run with the benchmark's own harness, images included. The intervals at the top overlap.
Each question's priors fitted on the benchmark's train split and applied at answer time; no weights change. Decider 1's score is its makers' own.
As the board lists them on 22 October 2026 (edition 0.4.1): half public vision benchmarks, half private images never published. The board ran our public weights.
Demos. Every guess, move and route below is one request to Amos, answered with how sure it is.
One request. A case and its questions in, typed answers out, from POST /v1/systemone.
Each question is yes/no, one of a list, several of a list, or a score. Every answer carries its probabilities, so your code can act on the sure ones and send the rest to a person.
curl https://api.amos.scira.ai/v1/systemone \
-H 'Content-Type: application/json' \
-d '{
"state": "Dana, 4 May: The desk arrived with a cracked leg. Can you send a new leg, or should I return the whole desk?",
"questions": {
"problem": {
"type": "choice",
"instructions": "What problem does the customer report?",
"criteria": {
"late_delivery": null,
"damaged_item": null,
"wrong_item": null
}
},
"wants_refund": {
"type": "noul",
"instructions": "The customer wants a refund."
}
},
"model": "amos-1-mini"
}'Four sizes, one API. The same request works on each; pick by how hard the decisions are and where they have to run.
Make your first decision in a minute.
Paste a case into the playground, or send one request from your own code. The weights are open, so you can run any size yourself.