Your Agent's Credit Score

Your agent is technically great. Buyers can't tell because every claim sounds the same. Get one independent score they actually trust — methodology public, evidence cited, embedded on your site.

Scores are re-assessed against each agent's public materials; changes of more than 5 points are checked by a person before they publish. We are not adding new agents right now. If your agent is already listed, claiming it is free, and so is the embed badge.

Claim an Existing Profile See the leaderboard

118 agents independently scoredRe-assessed from public materials

10 enterprise vendors evaluatedSalesforce · Microsoft · AWS · Google · IBM

Open methodology · 4-pillar rubricVersioned, evidence-cited, auditable

One number a buyer can act on.

A weighted score across 4 dimensions buyers actually care about — does it work, is it fast enough, can they afford it, and does it stay consistent. Every input is auditable, every weight is published, every recompute is timestamped. No marketing math.

Reliability

35%

Task success signals assessed on the published rubric — does the agent finish the job.

Latency

25%

Latency assessed from published performance characteristics, and measured directly (p50 / p95) once an agent connects production telemetry.

Cost Efficiency

25%

Tokens and API calls per completed task — how much it actually costs to run at scale.

Consistency

15%

Determinism controls in published materials, and variance across real traffic once telemetry connects — predictable output, or roll-the-dice each time.

Read the full methodology →

How scoring works

Every agent is assessed on the same published rubric — a bounded multi-model review with a deterministic 4-dimension composite. We publish the weighting, the per-dimension breakdown, and the assessor rationale — so the number can be audited, not just trusted.

Read the full methodology →

What you get, free

There is no paid tier. Nobody pays for rank, badges, or placement, and every agent runs through the same scoring pipeline.

Public listing on the leaderboard
Once scored, your agent appears on the leaderboard with its evidence class disclosed.
A scored profile with the full breakdown
Dimension-level scores and the assessor rationale behind them.
Embeddable score badge
An SVG badge for your README or site that tracks your current score.
Claim your listing
Verify ownership to update your profile and respond to reviews.
Improve dashboard for claimed owners
A ranked list of the changes most likely to move your score.
API keys
Programmatic access to scores at 100 requests per minute per key.

Claim your agent

Already listed?

Scores are re-assessed against each agent's public materials; changes of more than 5 points are checked by a person before they publish. We are not adding new agents right now. If your agent is on the leaderboard, claim the profile to respond to reviews and see your ranked fixes.

Claim an Existing Profile