promptfoo/examples/dbrx-benchmark/promptfooconfig.yaml

# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: DBRX model benchmarking against Mixtral and GPT-4o-mini

prompts:
  - 'Think deeply and answer concisely: {{query}}'

providers:
  - id: openrouter:databricks/dbrx-instruct
    config:
      temperature: 0
  - id: openrouter:mistralai/mixtral-8x7b-instruct
    config:
      temperature: 0
  - id: openai:gpt-4.1-mini
    config:
      temperature: 0

tests:
  - vars:
      query: 'What is the capital of France?'
    assert:
      - type: contains
        value: 'Paris'
  - vars:
      query: 'Explain the theory of relativity.'
    assert:
      - type: contains
        value: 'Einstein'
  - vars:
      query: 'Write a poem about the sea.'
    assert:
      - type: llm-rubric
        value: 'The poem should evoke imagery such as waves or the ocean.'
  - vars:
      query: 'What are the health benefits of eating apples?'
    assert:
      - type: contains
        value: 'vitamin'
  - vars:
      query: "Translate 'Hello, how are you?' into Spanish."
    assert:
      - type: similar
        value: 'Hola, ¿cómo estás?'
  - vars:
      query: 'Output a JSON list of colors'
    assert:
      - type: is-json
      - type: latency
        threshold: 5000