Belebele

What it measures

Parallel multiple-choice reading comprehension benchmark spanning 122 language variants linked to FLORES-200.

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

Average reading-comprehension accuracy over 122 language variants. Source headings distinguish few-shot, supervised and zero-shot conditions; model size and variant are retained.

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

Average reading-comprehension accuracy over 122 language variants. Source headings distinguish few-shot, supervised and zero-shot conditions; model size and variant 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.