AGIEval

AGIEval is a benchmark for general reasoning and comprehension. The official description says: "AGIEval - human-level standardized tests (SAT, LSAT, GRE, etc.)". Below we describe in simple words what benchmarks of this type generally examine.

AGIEval 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: AGIEval - human-level standardized tests (SAT, LSAT, GRE, etc.). 3-5-shot.

What is the AGIEval benchmark?

AGIEval is a benchmark for general reasoning and comprehension. The official description says: 'AGIEval - human-level standardized tests (SAT, LSAT, GRE, etc.)'. Below we describe in simple words what benchmarks of this type generally examine.

What does AGIEval test?

AGIEval 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 AGIEval 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 AGIEval data and scores?

The official source is https://arxiv.org/abs/2304.06364. 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/agieval/scores) or pull it directly from the Open LLM Radar API with any HTTP client.