reasoning benchmark
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.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
LSAT leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 88.0% | 100.0% | 1 | C |
LSAT highlights
The top published results on this benchmark's own scale.
What is LSAT?
Definition and scoring fields from the benchmark registry.
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.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- LSAT
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- lsat|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about LSAT.
Which model scores highest on LSAT?
GPT-4 is currently ranked first with 88.0%.
What does LSAT measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.