Agentic benchmark

ReviewBench leaderboard

Every model the catalog carries a published ReviewBench value for, ranked by that value.

CategoryAgentic

MeasureGrounded precision, recall, and F1; augmented metrics

Tasks219 pull requests across 187 repositories and 19 languages

Published byReviewBench: An open benchmark for AI code review

Measures how reliably code-review agents identify useful issues in real pull requests while avoiding false positives.

No model in the catalog has a published ReviewBench score.

The benchmark is defined by ReviewBench: An open benchmark for AI code review, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

About ReviewBench

What the benchmark measures and how its value is published, from the source’s own record.

What is ReviewBench?

ReviewBench is an agentic benchmark published by ReviewBench: An open benchmark for AI code review. Measures how reliably code-review agents identify useful issues in real pull requests while avoiding false positives. Its evaluation set is described by the source as 219 pull requests across 187 repositories and 19 languages.

How is ReviewBench scored?

Each model's result is published by ReviewBench: An open benchmark for AI code review as grounded precision, recall, and F1; augmented metrics. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.

All leaderboards · Agentic capability leaderboard

Explore models

Top 1-5

Top 6-10

Featured

Capabilities

Benchmarks

Compare

Featured model comparisons

Featured provider comparisons

Articles