Amos 1 medium

A 9B decision model. Give it a case (text, JSON or a photo) and a schema of typed questions; it answers every question in one forward pass, each with a probability for every answer you allow. It writes no text, so there is nothing to parse and no malformed output. Fast and accurate: level with the large on typed decisions in half its server time. The right default for most production decisions.

Part of the Amos 1 family: large · medium · small · mini. Playground · API docs · Model page

Results

Typed decisions, test split: 2,000 decisions from four workflows it never trained on, zero-shot.

	Accuracy	KL ↓	Brier ↓
Amos 1 medium	76.5%	0.151	0.080
Microsoft-Decision-1 (closed weights)	79.5%	0.318
Decider 1 (its makers' number)	76.8%	0.096
Perplexity Decider v1.1	73.9%	0.466
Clef (Cloudflare)	72.5%	0.191

Rivals run by us on the same 2,000 decisions, except Decider 1, whose number is its makers' own.

With each question's priors fitted on the benchmark's own train split and applied at answer time (the weights do not change), as Decider 1 also reports: 76.7% (Decider 1: 80.1%).

Decision Bench, all 1,071 real records, images included, run with the benchmark's own harness: 89.1%. The leaderboard lists Perplexity Decider v1.1 at 94.5%, DeepSeek V4.1 Flash and Gemini 3.5 Flash at 94.2%, Jev 1.13 at 93.8%.

Decision Index 0.3, public part, with the board's own kit: 52.55. The board's ranking adds private tests that only its maintainers run.

Other benchmarks, as served
JevBench public easy / standard / hard	100.0 / 98.6 / 73.0
Ten public benchmarks (RAGTruth, JudgeBench, Belebele, WinoGrande, ContractNLI, TruthfulQA, Circa, Financial PhraseBank, TabFact, BBH)	84.3%
AG News / DAIR Emotion / Banking77 (77 labels)	88.1 / 56.4 / 90.7
Server time, median, three-question request	61 ms

Use

Hosted, no key: POST https://api.amos.scira.ai/v1/systemone with "model": "amos-1-medium".

Or run it yourself. The serving package is in serve/ (Python 3.12, PyTorch 2.14; versions pinned to the ones these numbers were measured with):

hf download mukaddamzaid/amos-1-medium --local-dir amos-1-medium
pip install ./amos-1-medium/serve
python -m amos.serve amos-1-medium --device cuda --port 8000 --max-len 131072
curl http://127.0.0.1:8000/v1/systemone -H 'Content-Type: application/json' -d '{
  "state": "Invoice INV-2231 for £306.00 was charged to my card twice. Please refund one.",
  "questions": {
    "refund": {"type": "noul", "instructions": "Is the customer asking for a refund?"},
    "team": {"type": "choice", "instructions": "Which team should handle this?",
             "criteria": {"billing": null, "technical": null, "sales": null}}
  }
}'

Question types: yes/no (noul), pick one (choice, up to 255 options), rate (score), pick any (multi), quote (span) and point (region, with a photo in images). It runs on a 24 GB GPU and reads up to 131,072 tokens per request; cases near that length need about 40 GB.

File	What
`model/` (weights, tokenizer, image processor, `heads.pt`)	The model
`calibration.json`	Quote decoding settings the server reads
`serve/`	The serving package (`amos.serve`)
`typed_decisions.json`	The typed-decisions test scores above