What it measures

Evaluates an LLM's ability to critique and correct reasoning, math, code, and factual generations.

Reading the measurement

F1 balances precision and recall. Check both: a system can miss relevant evidence or include unsupported material, and those errors have different consequences. Keep the matching rule, averaging policy and denominator fixed.

Published evaluation

Critiquing · zero-shot answer-only; CriticBench · Critiquing · zero-shot answer-only. The source’s task split, model configuration and scoring units are retained.

Where this fits in an evaluation suite

Format compliance, preference, truthfulness, and safety require separate measurements. Keep desirable writing style from masking factual errors.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Critiquing · zero-shot answer-only; CriticBench · Critiquing · zero-shot answer-only. The source’s task split, model configuration and scoring units are retained.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. CriticBench: Benchmarking LLMs for Critique-Correct Reasoning — published result table ↗

    Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang · 2024

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.