MolecularIQ

An OpenCompass wrapper for MolecularIQ, which evaluates chemical reasoning over molecular structures with symbolic verification.

Also known as: Molecular IQ, OpenCompass molculariq

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.
Categorydomain
Subcategorysymbolically verified molecular graph reasoning
Page statusactive
Metrictask-specific symbolic correctness and generation scores
Directionhigher_is_better
Unit%
Dataset size5111
PublisherML-JKU MolecularIQ authors

What it measures

MolecularIQ asks models to reason about molecules represented through SMILES and related symbolic forms. Its task families include counting properties, locating indexed atoms or groups, enumerating rings, and generating molecules under constraints. The benchmark focuses on questions whose answers can be checked by symbolic chemistry software rather than by a language-model judge.

Task format

OpenCompass exposes count, index, and generation configurations. Prompts require JSON inside answer tags, exact question key names, zero-based heavy-atom indices, and empty lists or zero counts when a feature is absent. Evaluators are separate for count, index, and generation tasks.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub