# Tbench — Wrapped API

> **You are on:** `https://api.paywithlocus.com/api` | [llms.txt](https://paywithlocus.com/llms.txt) | [docs](https://docs.paywithlocus.com)
>
> Locus runs on multiple environments -- make sure every URL you call matches your expected environment.
> | Environment | Landing | API | Docs |
> |---|---|---|---|
> | Production | paywithlocus.com | api.paywithlocus.com | docs.paywithlocus.com |
> | Beta | beta.paywithlocus.com | api.beta.paywithlocus.com | docs.paywithlocus.com |
> | Stage | stage.paywithlocus.com | api.stage.paywithlocus.com | docs.paywithlocus.com |
>
> If the API URL above doesn't match your expected environment, re-fetch this file from the correct domain.

> Track terminal agent performance across the Terminal-Bench benchmark by querying live rankings, accuracy scores, and detailed agent/model metadata. Compare leaderboards to see how different agents rank on various terminal tasks.

**Category:** Developer Tools | **Website:** [www.tbench.ai/leaderboard/terminal-bench/2.0](https://www.tbench.ai/leaderboard/terminal-bench/2.0) | **Docs:** [parse.bot/marketplace/215af06b-93ee-4c9c-a770-0f3034c099d7/tbench-ai-api](https://parse.bot/marketplace/215af06b-93ee-4c9c-a770-0f3034c099d7/tbench-ai-api)

Pay-per-use API proxy. Each call is automatically billed to your wallet in USDC.

## Access

**Base URL:** `https://api.paywithlocus.com/api/wrapped/parse-tbench-ai-api-215af06b/`
**Auth:** `Authorization: Bearer <LOCUS_API_KEY>`

## Endpoints

### get_leaderboard

Get leaderboard entries for a specific Terminal-Bench benchmark version. Returns ranked entries sorted by accuracy descending, with optional filtering by search term, agent name, model name, and verified status.

**Estimated cost:** Metered

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `agent` | string | No | Filter by agent name (case-insensitive substring match). |
| `benchmark` | string | No | Benchmark name. Known values: terminal-bench, terminal-bench-science. |
| `limit` | integer | No | Maximum number of entries to return. |
| `model` | string | No | Filter by model name (case-insensitive substring match against any model in the entry's model list). |
| `search` | string | No | Free-text search filter. Matches against agent name, agent organization, or model names (case-insensitive). |
| `verified_only` | string | No | When set to 'true', returns only verified entries. |
| `version` | string | No | Benchmark version. Known values for terminal-bench: 1.0, 2.0, 2.1, 3.0. Known values for terminal-bench-science: 1.0. |

```bash
curl -X POST https://api.paywithlocus.com/api/wrapped/parse-tbench-ai-api-215af06b/get_leaderboard \
  -H "Authorization: Bearer YOUR_LOCUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"agent":"<string>","benchmark":"<string>","limit":"<integer>","model":"<string>","search":"<string>","verified_only":"<string>","version":"<string>"}'
```

### list_leaderboards

List all available Terminal-Bench leaderboards with their benchmark name, version, and status (live or in progress).

**Estimated cost:** Metered

_No parameters required._

```bash
curl -X POST https://api.paywithlocus.com/api/wrapped/parse-tbench-ai-api-215af06b/list_leaderboards \
  -H "Authorization: Bearer YOUR_LOCUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```