Evaluation
Diagnostics Guide
How the diagnostic judge works, what it flags, and how to act on findings in comparisons, evaluations, and benchmarks.
This guide is coming soon. In the meantime, see the Scoring Guide for a detailed walkthrough of how the diagnostic judge works and real examples of findings.
See your pipeline diagnostics
Run an evaluation or benchmark and get automatic pipeline health findings alongside every score.
See pricingWhat’s next
Scoring Guide
How LLM Prover calculates scores, what affects them, and how to use the diagnostic judge to find out why.
Rubric Writing Guide
How to write criteria that produce reliable, consistent judge scores -- and how to fix them when they don't.
Benchmark Guide
Save a run configuration, schedule it on a cadence, and track quality and cost drift over time.
Evaluations Guide
Score model outputs against a rubric or gold standard answer and get per-criterion reasoning.