# Benchmark

URL: https://docs.hanzo.ai/docs/mcp-tools/benchmark

> benchmark: 9 operations.

Also for this capability: [API](https://docs.hanzo.ai/docs/openapi/benchmark) · [CLI](https://docs.hanzo.ai/docs/cli/benchmark) · **MCP** · [SDKs](https://docs.hanzo.ai/docs/sdks)

benchmark: 9 operations. Name one in "op" and pass that operation's own arguments in "input". describe returns an operation's input schema.

|               |                                                                                                                           |
| ------------- | ------------------------------------------------------------------------------------------------------------------------- |
| **Tool**      | `benchmark`                                                                                                               |
| **Address**   | `https://api.hanzo.ai/v1/mcp`                                                                                             |
| **Method**    | `tools/call` (JSON-RPC 2.0)                                                                                               |
| **Arguments** | 2, 1 required                                                                                                             |
| **Operation** | `GET /v1/benchmark/catalog` · `GET /v1/benchmark/compare` · `GET /v1/benchmark/history` · `GET /v1/benchmark/leaderboard` |
| **Product**   | [benchmark](https://docs.hanzo.ai/docs/openapi/benchmark)                                                                 |

## Arguments

| Field   | Type     | Required | Default | Values | Description                 |
| ------- | -------- | -------- | ------- | ------ | --------------------------- |
| `input` | `object` | —        | —       | —      | arguments for the chosen op |
| `op`    | `string` | **yes**  | —       | —      | —                           |

`tools/list` declares a type, a description, which fields are required and an enumerated value set for each field and nothing further, and every column above is MCP's own. This tool takes an operation name and that operation's arguments, so what the document constrains is what goes inside `input`, field by field, on the operation you name — ask `describe` for that. A `—` means MCP does not constrain the field.

## Call it

A `tools/call` carries every argument in one flat object — nothing binds to a path or a query string. This call carries exactly the arguments the operation requires, so it is the smallest one that can run.

```bash
curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "benchmark",
         "arguments": {
           "op": "get_benchmark_catalog"
         }
       }
     }'
```

Values are the operation's own defaults and enumerated values where it declares them, and a `<placeholder>` where neither source declares one. `tools/list` needs no credential; `tools/call` does — called without one MCP answers HTTP 200 with a JSON-RPC result whose `isError` is set and whose text says what was missing. [How to get a key →](https://docs.hanzo.ai/docs/mcp-tools#credentials)

## The operation behind it

`benchmark` dispatches to 9 operations. 4 of them MCP names exactly as the document ids them, and those are below; for the rest MCP has its own verb, which `describe` resolves.

| Operation                   | Route                           | Product                                                   | Summary                                                                                                                                                                                                                       |
| --------------------------- | ------------------------------- | --------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `get_benchmark_catalog`     | `GET /v1/benchmark/catalog`     | [benchmark](https://docs.hanzo.ai/docs/openapi/benchmark) | The canonical public benchmarks this arena runs — the id, title, axis, item count and upstream source of each, with native marking the ones the standardized harness runs today; the rest are registered and adapter-pending. |
| `get_benchmark_compare`     | `GET /v1/benchmark/compare`     | [benchmark](https://docs.hanzo.ai/docs/openapi/benchmark) | The ONLY valid arm-vs-arm test: it pairs the two models on the items BOTH completed, and answers rescue and damage counts with an exact-McNemar p.                                                                            |
| `get_benchmark_history`     | `GET /v1/benchmark/history`     | [benchmark](https://docs.hanzo.ai/docs/openapi/benchmark) | Returns each model's measured score per run over time, oldest first, with the change between runs.                                                                                                                            |
| `get_benchmark_leaderboard` | `GET /v1/benchmark/leaderboard` | [benchmark](https://docs.hanzo.ai/docs/openapi/benchmark) | Answers one row per model for the benchmark named — what our own harness measured, beside what the vendor claims, and the gap between them.                                                                                   |

The same capability over plain HTTP is in the [benchmark API reference](https://docs.hanzo.ai/docs/openapi/benchmark), on `https://api.hanzo.ai`.

---

[All 120 tools](https://docs.hanzo.ai/docs/mcp-tools/all-tools) · [MCP](https://docs.hanzo.ai/docs/mcp-tools) · [API reference](https://docs.hanzo.ai/docs/openapi)

Generated from `tools/list` on `https://api.hanzo.ai/v1/mcp` — 120 tools captured 2026-09-30.