LSAT
LSAT (Law School Admission Test) benchmark evaluating complex reasoning capabilities across three challenging tasks: analytical reasoning, logical reasoning, and reading comprehension. The LSAT measures skills considered essential for success in law school including critical thinking, reading comprehension of complex texts, and analysis of arguments.
Progress Over Time
Interactive timeline showing model performance evolution on LSAT
State-of-the-art frontier
Open
Proprietary
LSAT Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  OpenAI | — | 33K | $30.00 / $60.00 |
Notice missing or incorrect data?
FAQ
Common questions about LSAT
LSAT (Law School Admission Test) benchmark evaluating complex reasoning capabilities across three challenging tasks: analytical reasoning, logical reasoning, and reading comprehension. The LSAT measures skills considered essential for success in law school including critical thinking, reading comprehension of complex texts, and analysis of arguments.
The LSAT paper is available at https://arxiv.org/abs/2108.00648. This paper provides detailed information about the benchmark methodology, dataset creation, and evaluation criteria.
The LSAT leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, GPT-4 by OpenAI leads with a score of 0.880. The average score across all models is 0.880.
The highest LSAT score is 0.880, achieved by GPT-4 from OpenAI.
1 models have been evaluated on the LSAT benchmark, with 0 verified results and 1 self-reported results.
LSAT is categorized under general, legal, and reasoning. The benchmark evaluates text models.