Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
Nothing to run from here
BenchLeader is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Daily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http benchleader-mcp https://www.benchleader.com/mcp
# 2 — ask your agent for something these tools do
# get_leaderboard, search_models, get_model and 4 more
BenchLeader costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BEAll 1 server
benchleader1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http benchleader-mcp https://www.benchleader.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
The BenchLeader Index leaderboard of large language models: a daily composite of independent public benchmarks, one row per model (its best reasoning-effort configuration) as on the homepage. Optionally rank by one category score (coding, agentic, reasoning, math, knowledge…), list every model × effort configuration, or filter to open-weights models or one developer. Paged.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Rank by this category score instead of the overall Index, e.g. coding, agentic, reasoning, math, knowledge, instruction, multimodal, long_context. |
| configurations | boolean | no | List every ranked model × reasoning-effort configuration rather than one row per model. |
| open_weights_only | boolean | no | Only models with downloadable weights. |
| developer | string | no | Only models from this developer, e.g. OpenAI, Anthropic, Google, DeepSeek. |
| limit | integer | no | How many rows to return (at most 100). |
| offset | integer | no | Rows to skip, for paging (use next_offset from the previous page). |
Find models by name, alias, id or developer ("opus", "gemini 4", "deepseek"). Returns each match's id, rank, Index and reasoning-effort configurations, for use with get_model and compare_models.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Model name, alias, id or developer. |
| limit | integer | no | How many matches to return (at most 25). |
One model's BenchLeader profile: Index and rank, category scores, list price, speed, latency, context window, its other reasoning-effort configurations, and its strongest independent benchmark results (each with its board rank, publisher and source link).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Model id ("claude-opus-5-5"), configuration id ("gpt-6-astra@max"), page URL or name. |
| effort | string | no | Reasoning-effort configuration to show (none, low, medium, high, xhigh, max…). Defaults to the best-ranked one. |
| results_limit | integer | no | How many benchmark results to return (at most 50). |
Head-to-head comparison of two models with BenchLeader's verdict: who leads on quality (a lead is claimed only outside the combined margin of error), price and speed ratios, category-by-category wins, when to choose each, and shared benchmark results. Links the comparison page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model_a | string | yes | First model: id, configuration id, page URL or name. |
| model_b | string | yes | Second model: id, configuration id, page URL or name. |
| effort_a | string | no | Reasoning effort for model_a (defaults to its best-ranked configuration). |
| effort_b | string | no | Reasoning effort for model_b (defaults to its best-ranked configuration). |
The benchmarks BenchLeader reads: what each measures, publisher, category, whether it feeds the Index (and its weight), how many models it covers, status and caveats. Filter by category or a search query. Paged.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Only this category, e.g. coding, agentic, reasoning, math, knowledge. |
| query | string | no | Search benchmark names, ids, aliases and publishers ("swe-bench", "arc", "epoch"). |
| in_index_only | boolean | no | Only benchmarks that feed the BenchLeader Index. |
| limit | integer | no | How many benchmarks to return (at most 100). |
| offset | integer | no | Rows to skip, for paging (use next_offset from the previous page). |
One benchmark: what it measures, unit, publisher and source, whether and how much it counts in the BenchLeader Index, status and caveats, and its top models (one row per model, best result first).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| benchmark | string | yes | Benchmark id ("gpqa_diamond"), name ("SWE-bench Verified"), alias or page URL. |
| limit | integer | no | How many top models to return (at most 25). |
What BenchLeader is, how the BenchLeader Index is computed, the current method version, data date and update cadence, coverage counts, licence and how to cite it.
No parameter schema on file.
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install BenchLeader or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.0.0 · scanned 1 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestcaeb1b23bfd952eb2a1470eb3172e71373f91a5c8d9bf2e937112fdb6431753f
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_leaderboard | no tags | |
| search_models | no tags | |
| get_model | no tags | |
| compare_models | no tags | |
| list_benchmarks | no tags | |
| get_benchmark | no tags | |
| about_benchleader | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestcaeb1b23bfd952eb
Scanned2026-11-01
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish BenchLeader can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.