Benchmark
The `hanzo benchmark` commands.
Also for this capability: API · CLI · MCP · SDKs
One honest score for any model, on the tests everyone quotes.
hanzo benchmark catalogEvery 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.
| Command | What it does |
|---|---|
hanzo benchmark catalog | Is the canonical public benchmarks this arena runs — the id, title, axis, item count and upstream source of each, with… |
hanzo benchmark history | Returns each model's measured score per run over time, oldest first, with the change between runs. |
hanzo benchmark leaderboard | Answers one row per model for the benchmark named — what our own harness measured, beside what the vendor claims, and… |
claims
| Command | What it does |
|---|---|
hanzo benchmark claims create | Records published claims: one to correct a number, many to import a leaderboard. |
hanzo benchmark claims get | Lists the effective published claims: what the leaderboard will use for each (benchmark, model) after the seed, the… |
compare
| Command | What 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
| Command | What it does |
|---|---|
hanzo benchmark presets create | Validates a router blend — its name, its arms, the rank they escalate through and the panel fan-out width — and answers… |
hanzo benchmark presets get | Are the router blends available to compose from — a named set of model arms, the rank they escalate through and the… |
runs
| Command | What 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?