Skip to content
Try Hanzo
Language: English (United States)

Evals

Measure model and agent quality.

Beta

01/ 07

Science

API
/v1/eval
Google Cloud
Vertex AI Eval
Evals
  • Open source
  • On-chain settlement

Read https://hanzo.ai/skill.md and use Hanzo Evals in my project. Start with: hanzo eval runs create

The service the session above is changing.

  1. hanzo eval runs create
  2. api.hanzo.ai/v1/eval
  3. Vertex AI Eval
api.hanzo.ai/v1/evalOpen in the console

Paste and ship

Paste this into any agent. It reads the skill manifest and calls Evals from there.

Read https://hanzo.ai/skill.md and use Hanzo Evals in my project. Start with: hanzo eval runs create

Agent promptapi/v1/eval

Science

Benchmark, grade, and regression-test models and agents. LLM-as-judge, golden sets, and drift detection with reproducible scorecards anchored on-chain.

Source
  1. Beta

    Evals

    Measure model and agent quality.

    Google CloudVertex AI Eval

    1. 01LLM-as-judge & golden sets
    2. 02Regression gates in CI
    3. 03Drift detection
    4. 04Anchored scorecards
    Open in the console
  2. Science

    Benchmark

  3. Science

    Research

  4. Science

    Datasets

  5. Science

    Experiments

  6. Science

    Scores

  7. Science

    Score Configs

Related capabilities

  1. 01Benchmark
  2. 02Research
  3. 03Datasets

A human signs a company into existence. After genesis, agents can run it.

Evals

Measure model and agent quality.

Talk to usapi.hanzo.ai/v1/evalSource