Modelsamos-1-small
Amos 1 smallBuilt for volume. Reads text, JSON and photos. Stays up for two hours after a request; waking takes about two minutes.
- Size2B
- Server time, median48 ms
- Context256K tokens
- Typed decisions, zero-shot69.5%
- Typed decisions, fitted74.4%
- Calibration, KL0.181
- Decision Index 0.3, public31.92
When to use it
- High volume, where speed matters most.
- Quotes and boxes as well as answers.
- Cases with photos.
- Cases up to 256K tokens.
Typed decisions
Accuracy on the 2,000-decision test split, zero-shot. We ran each rival on the same 2,000 decisions; Decider 1's score is its makers' own. Frontier language models asked the same questions score between 73 and 78.
- Microsoft-Decision-1closed weights, KL 0.31879.5
- Decider 176.8
- Amos 1 medium76.5
- Amos 1 large76.1
- Perplexity Decider v1.173.9
- Clef72.5
- GPT-6 Luna71.9
- Amos 1 small69.5
- Amos 1 mini64.6
Quotes and photos
- Invoice totals quoted exactly9 / 10
- Box centred on the named object, RefCOCO94.2%
- Boxes covering at least half the object, RefCOCO77.2%
- Box centred on the named object, COCO97.5%
Limits
- Seven points behind medium on typed decisions.
- Weaker on questions that need broad knowledge.
- Ratings are its least reliable answers.
- English only.
Quick start
Name the model in the model field.
curl https://api.amos.scira.ai/v1/systemone \
-H 'Content-Type: application/json' \
-d '{
"model": "amos-1-small",
"state": "Hi, invoice INV-2231 for £306.00 was charged to my card twice this morning. Please refund one of them today.",
"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
}
},
"amount": {
"type": "span",
"instructions": "How much was charged?"
}
}
}'