Symbol Interpretation

BIG-bench Lite task: pick which sentence correctly describes a 'structure' — a sequence of six emoji pieces — across five adversarial variants.

Also known as: SIT

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryreasoning
Subcategorystructured visual/logical reasoning via emoji-symbol interpretation (BIG-bench Lite)
Page statusunknown
Metricmultiple_choice_grade
Directionhigher_is_better
Dataset size990
Dataset licenceApache-2.0
PublisherGoogle (BIG-bench collaboration)

What it measures

The model is given a "structure": a sequence of six pieces represented by emojis, standing in for objects in a simple constructed world. It must choose, from a set of candidate sentences, the one that correctly and consistently describes two given structures. The task is split into five subtasks that vary how directly the emojis map to their described meaning: a "plain" version with direct emoji-to-name correspondence, an "adversarial" version with intentionally mismatched emoji-name associations, a "tricky" version with reversed object descriptions, and two "agnostic" versions that substitute generic placeholders for either the names or the emojis. Within each subtask, items escalate across difficulty tiers covering simple quantification, logical operators, and positional relationships between pieces.

Task format

Multiple-choice, zero-shot; each item asks which sentence is consistent with two given emoji structures.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub