ClimaQA

An automated framework producing 566 expert-verified (Gold) and 3,000 synthetic (Silver) climate-science QA items across multiple-choice, cloze and free-form formats.

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
Subcategoryclimate science question answering
Page statusactive
Metricaccuracy (MCQ/cloze, LLM-graded exact-consistency) and LLM-graded closeness (free-form)
Directionhigher_is_better
Unit%
Dataset size566
Dataset licenceApache-2.0 (stated on both the GitHub repository and the Hugging Face dataset card)
PublisherUniversity of California, San Diego

What it measures

ClimaQA tests whether a model holds accurate, textbook-level climate-science knowledge and can apply it across three question formats. Its authors built ClimaGen, an LLM-driven pipeline that generates question-answer pairs from graduate climate-science textbooks with climate scientists reviewing the output, then used it to produce two datasets under the ClimaQA name: ClimaQA-Gold, a smaller expert-annotated set, and ClimaQA-Silver, a larger fully synthetic set for scale. Within each, questions are further split by cognitive demand into Base (factual recall), Reasoning (multi-step scientific reasoning) and Hypothetical (scenario application) tiers.

Task format

Three question formats drawn from the same underlying question bank: multiple-choice (four options, a-d), cloze (fill in a missing word or short phrase), and free-form question answering (an open-ended response with no options). All three are scored by having a separate LLM grader compare the model's answer against the gold answer under format-specific grading instructions, rather than by simple string matching.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub