ARC-c

ARC-c is a benchmark for general reasoning and comprehension. The official description says: "AI2 Reasoning Challenge (Challenge set) - grade-school science questions". Below we describe in simple words what benchmarks of this type generally examine.

ARC-c measures general reasoning and comprehension. In detail, it checks:

• drawing the right conclusion from a passage or scenario
• commonsense judgement about everyday situations and words
• counting, comparing and reasoning over several facts at once
• avoiding shortcuts that memorise answers instead of reasoning

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: AI2 Reasoning Challenge (Challenge set) - grade-school science questions. 25-shot.

What is the ARC-c benchmark?

ARC-c is a benchmark for general reasoning and comprehension. The official description says: 'AI2 Reasoning Challenge (Challenge set) - grade-school science questions'. Below we describe in simple words what benchmarks of this type generally examine.

What does ARC-c test?

ARC-c mainly measures general reasoning and comprehension. Concretely, it checks: drawing the right conclusion from a passage or scenario; commonsense judgement about everyday situations and words; counting, comparing and reasoning over several facts at once.

How is the ARC-c score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get ARC-c data and scores?

The official source is https://arxiv.org/abs/1911.01547. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/arc-c/scores) or pull it directly from the Open LLM Radar API with any HTTP client.