Hanzo AI

Benchmark

The `hanzo benchmark` commands.

Also for this capability: API · CLI · MCP · SDKs

One honest score for any model, on the tests everyone quotes.

API reference →

hanzo benchmark catalog

Every command takes --json for the raw response and --help for its own flags. Sign in once with hanzo auth login; the commands below use that session, and the org they act in is the one it carries.

CommandWhat it does
hanzo benchmark catalogIs the canonical public benchmarks this arena runs — the id, title, axis, item count and upstream source of each, with…
hanzo benchmark historyReturns each model's measured score per run over time, oldest first, with the change between runs.
hanzo benchmark leaderboardAnswers one row per model for the benchmark named — what our own harness measured, beside what the vendor claims, and…

claims

CommandWhat it does
hanzo benchmark claims createRecords published claims: one to correct a number, many to import a leaderboard.
hanzo benchmark claims getLists the effective published claims: what the leaderboard will use for each (benchmark, model) after the seed, the…

compare

CommandWhat it does
hanzo benchmark compare --a <a> --b <b>Is the ONLY valid arm-vs-arm test: it pairs the two models on the items BOTH completed, and answers rescue and damage…

presets

CommandWhat it does
hanzo benchmark presets createValidates a router blend — its name, its arms, the rank they escalate through and the panel fan-out width — and answers…
hanzo benchmark presets getAre the router blends available to compose from — a named set of model arms, the rank they escalate through and the…

runs

CommandWhat it does
hanzo benchmark runs --benchmarks '["<benchmarks>"]'Admits and queues a benchmark run against a model or your own endpoint, and answers 202 with the receipt.

How is this guide?

On this page