Connect your tools
to BenchLM.

Query model and benchmark catalogs with a free account. Use the same key and allowance across REST and MCP.

1,000: successful reads per month
$0: no payment details required

Your allowance renews on your account anniversary each month.

Sign in by email

Enter your email to receive a one-time code. New accounts start on Free.

Data access

Free

Monthly allowance

— reads left

API keys

All your keys share one account allowance. You can keep up to five active keys.

Active API keys
Key ID	Created	Action

Connect a client

Use a Bearer token with your API key. Keep keys in your client’s secret settings.

MCP endpoint
REST base URL
Authorization header: Bearer YOUR_DATA_KEY

MCP clients should use the Streamable HTTP transport. For REST, start with this catalog query:

Your plan

Data Pro $49 USD / month

100,000 successful reads per month, plus recorded BenchAlign scores and rankings, cleared benchmark measurements, and catalog events. Check coverage before choosing a plan.

Not available for purchase yet.

Radar + Data $59 USD / month

Radar and Data Pro, with separate API keys and allowances, billed together. Existing subscriptions keep their terms until period end before bundle checkout opens.

Bundle checkout is being prepared.

What you can query

Free access includes model identities and benchmark catalog metadata. Numeric historical data requires Data Pro and approved coverage for the requested fields.

REST endpoints and MCP tools
Data	REST endpoint	MCP tool
Model catalog	`GET /v1/models`	`benchlm_list_models`
One model	`GET /v1/models/{identifier}`	`benchlm_get_model`
Benchmark catalog	`GET /v1/benchmarks`	`benchlm_list_benchmarks`
Available historical coverage	`GET /v1/coverage`	`benchlm_history_coverage`
Stored BenchAlign rank history	`GET /v1/history/rank_history`	`benchlm_rank_history`
Benchmark measurements over time	`GET /v1/history/benchmark_history`	`benchlm_benchmark_history`
Benchmark additions and changes	`GET /v1/history/benchmark_events`	`benchlm_benchmark_events`
Stored ranking at a date	`GET /v1/history/ranking_snapshot`	`benchlm_ranking_snapshot`

Historical delivery is not available yet.

Use catalog IDs to choose a model and benchmark. Ranking history takes modelKey; benchmark measurements take modelKey, category and benchmarkKey. Add since, through and limit to choose a page. A ranking snapshot takes at. Responses include the next cursor when another page is available.

Historical queries return up to 500 rows per page and cover up to 90 days per request. Dates describe saved repository states; they are not claims about when a source first published a result. A ranking snapshot contains the approved subset and identifies its coverage.

Rankings are stored BenchAlign rankings. Benchmark history contains measurements; historical leaderboard positions for individual benchmarks are not included.

Each successful data page uses one read. MCP discovery, coverage and usage checks, and unsuccessful queries do not use your monthly allowance. Free allows 10 requests per minute; Data Pro allows 60. API key rotation does not reset usage.