What it measures

Dynamically updated QA benchmark testing fast-changing world facts and false-premise debunking.

Reading the measurement

Accuracy is only part of the picture. Inspect unsupported answers, abstentions, language coverage and the evidence available to the model. A confident response can still be wrong, and a broad average can hide a specialist gap.

Published evaluation

Source overall accuracy under the named search and grading regime. Time-sensitive facts, evaluation date and strict hallucination handling limit cross-snapshot comparisons.

Where this fits in an evaluation suite

Read accuracy together with error and abstention rates. Domain averages can hide language gaps, specialist failures, and poorly calibrated confidence.

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

Source overall accuracy under the named search and grading regime. Time-sensitive facts, evaluation date and strict hallucination handling limit cross-snapshot comparisons.

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. FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation — published result table ↗

    Vu, Tu, Iyyer, Mohit, Wang, Xuezhi, Constant, Noah, Wei, Jerry, Wei, Jason et al. · 2023

    All 11 authors

    Vu, Tu, Iyyer, Mohit, Wang, Xuezhi, Constant, Noah, Wei, Jerry, Wei, Jason, Tar, Chris, Sung, Yun-Hsuan, Zhou, Denny, Le, Quoc, Luong, Thang

Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.