Skip to content

Playground

Which answer is more reliable?

Which answer is more reliable? Picks the more accurate one. Swap the order of the two answers and the verdict stays the same.

Related articleAn LLM-as-a-Judge Alternative: Use a Decision Model as the First Pass

Sample results do not change with the selected model.

Request

state
application/json
{  "question": "What is the boiling point of water?",  "answer_a": "At standard atmospheric pressure water boils at 100°C; higher altitude lowers the boiling point, about 70°C on Everest.",  "answer_b": "Water always boils at 100°C, first measured by Einstein in Geneva in 1889."}

Results

Sample data
Compare two examples

These two examples differ by one detail. The result changes with them.

What changedThe two answers swap places

These results are sample data, not a live model run. Sign in to try them with your own content.

Swap the order of the two answers and the verdict stays the same.

winner: B · Answer B is better → A · Answer A is better factuality: 0 · Seriously wrong → 3 · Fully accurate
winnerchoice
A · Answer A is better
Confidence per option
Answer A is better
91%
Answer B is better
4%
Tie
5%
factualityscore
3 · Fully accurate
Confidence per option
0 · Seriously wrong
1%
1 · Clear errors
3%
2 · Mostly accurate
24%
3 · Fully accurate
72%

Copy the code

Set SYSTEM_ONE_API_KEY. The snippet uses a published catalog model id.

Request JSON
application/json
{"model":"decider-v1.1","state":{"question":"What is the boiling point of water?","answer_a":"At standard atmospheric pressure water boils at 100°C; higher altitude lowers the boiling point, about 70°C on Everest.","answer_b":"Water always boils at 100°C, first measured by Einstein in Geneva in 1889."},"questions":{"winner":{"type":"choice","instructions":"Which answer is better overall?","criteria":{"A":"Answer A is better","B":"Answer B is better","tie":"Tie"}},"factuality":{"type":"score","instructions":"Rate the factual accuracy of answer A.","criteria":["Seriously wrong","Clear errors","Mostly accurate","Fully accurate"]}}}
cURL · POST /v1/systemone
sh
curl "https://system-one.dev/v1/systemone" \  -H "Authorization: Bearer $SYSTEM_ONE_API_KEY" \  -H 'Content-Type: application/json' \  -H 'Idempotency-Key: saved-operation-id' \  --data '{"model":"decider-v1.1","state":{"question":"What is the boiling point of water?","answer_a":"At standard atmospheric pressure water boils at 100°C; higher altitude lowers the boiling point, about 70°C on Everest.","answer_b":"Water always boils at 100°C, first measured by Einstein in Geneva in 1889."},"questions":{"winner":{"type":"choice","instructions":"Which answer is better overall?","criteria":{"A":"Answer A is better","B":"Answer B is better","tie":"Tie"}},"factuality":{"type":"score","instructions":"Rate the factual accuracy of answer A.","criteria":["Seriously wrong","Clear errors","Mostly accurate","Fully accurate"]}}}'
TypeScript
TypeScript
// npm install @system-one-ai/core@0.6.0 @system-one-ai/transport-fetch@0.6.0 @system-one-ai/adapter-system-one@0.6.0import { createSystemOne, choice, score, booleanQuestion } from '@system-one-ai/core';import { systemOneAdapter } from '@system-one-ai/adapter-system-one';import { createFetchTransport } from '@system-one-ai/transport-fetch';const client = createSystemOne({  baseURL: "https://system-one.dev/v1",  apiKey: process.env.SYSTEM_ONE_API_KEY!,  model: "decider-v1.1",  adapter: systemOneAdapter,  transport: createFetchTransport(),  timeoutMs: 30_000,  maxRetries: 0,});const result = await client.evaluate({  state: {    "question": "What is the boiling point of water?",    "answer_a": "At standard atmospheric pressure water boils at 100°C; higher altitude lowers the boiling point, about 70°C on Everest.",    "answer_b": "Water always boils at 100°C, first measured by Einstein in Geneva in 1889."  },  questions: {  winner: choice("Which answer is better overall?", {    A: "Answer A is better",    B: "Answer B is better",    tie: "Tie",  }),  factuality: score("Rate the factual accuracy of answer A.", ["Seriously wrong", "Clear errors", "Mostly accurate", "Fully accurate"]),  },}, { headers: { 'Idempotency-Key': crypto.randomUUID() } });result.answers.winner.choiceresult.answers.factuality.scoreresult.response.requestId;