Amos

Modelsamos-1-medium

Amos 1 mediumFast and accurate. Right for most workloads.

Try it in the playground
  1. Size9B
  2. Server time, median61 ms
  3. Context128K tokens
  4. Typed decisions, zero-shot76.5%
  5. Typed decisions, fitted76.7%
  6. Calibration, KL0.151
  7. Decision Bench89.1%
  8. Decision Index 0.3, public52.55

When to use it

  • Most production decisions.
  • Level with large on typed decisions.
  • Hard questions in half of large’s time.
  • Cases up to 128K 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.

  1. Microsoft-Decision-1closed weights, KL 0.31879.5
  2. Decider 176.8
  3. Amos 1 medium76.5
  4. Amos 1 large76.1
  5. Perplexity Decider v1.173.9
  6. Clef72.5
  7. GPT-6 Luna71.9
  8. Amos 1 small69.5
  9. Amos 1 mini64.6

Limits

  • Behind large on questions that take several steps.
  • Quote and photo scores coming soon.
  • 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-medium",
  "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?"
    }
  }
}'

The other models