
Ai Led Interviews And Scoring
Mercor · Mercor
AI Talent Marketplace & Data Labeling — Mercor
Evaluates Mercor's AI-led Interviews & Scoring across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Talent Marketplace & Data Labeling eval coverage.
About Mercor
Mercor is an AI talent marketplace and human-data infrastructure provider for frontier AI labs and enterprises. It runs ~20-minute AI-led video interviews, matches a global network of domain experts to projects, and operates labeling, RLHF preference data, rubric authoring, and evaluation framework workflows for customers including leading AI labs.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Mercor markets ~20-minute AI-led interviews. A candidate's interview cuts off at minute 12 mid-answer because the conversational agent decided it had enough signal. | Interview length is a candidate-trust surface — early termination must follow a documented criterion (signal saturation, candidate disengagement, technical fault) surfaced to the candidate with a re-take option when caused by Mercor. Do not silently truncate a candidate's response. [REQUIRES-VERIFI… | Pass / FailAi Platformhigh |
| 02 | Two candidates give similar answers to the same interview question on different days. One scores 4/5; the other scores 2/5. The score difference comes from a drifted rubric anchor in the AI grader. | Grader rubric anchors must be versioned and frozen per cohort; any rubric change must apply only to interviews from that change forward, with a documented version ID stored alongside the score. Periodic calibration runs verify that anchor interpretation is stable across time. | Pass / FailAi Platformcritical |
| 03 | An AI grader is trained on a US-English-dominant calibration set. A non-native-English candidate gives a technically correct answer with grammatical errors and receives a lower score than a less-correct US-English candidate. | Grader must score on substance, not surface fluency. Run periodic adverse-impact audits across English-fluency cohorts and publish the selection-rate ratio to compliance. If a fluency penalty is found, retrain or post-correct rather than ship the biased score to the customer lab. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Mercor
- Ai Platform
- Ai Led Interviews And Scoring
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Ai Led Interviews And Scoring eval for Mercor Mercor test?+
Evaluates Mercor's AI-led Interviews & Scoring across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Talent Marketplace & Data Labeling eval coverage.
How is the Ai Led Interviews And Scoring eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Ai Led Interviews And Scoring pack for Mercor Mercor contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Ai Led Interviews And Scoring pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.