PRBench-Legal
PRBench-Legal - professional reasoning benchmark for legal domain. Evaluated using gemini-3.1-pro-preview.
Category
General Capabilities
Score type
percent
Scale
relative
higher is better
Models tested
1
What is PRBench-Legal?
PRBench-Legal is a benchmark for broad everyday usefulness across domains. The official description says: "PRBench-Legal - professional reasoning benchmark for legal domain". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
PRBench-Legal measures broad everyday usefulness across domains. In detail, it checks:
- realistic, open-ended requests from varied professional fields
- correct, well-structured and helpful responses
- consistent quality across very different task types
- judgement and advice quality, not just factual recall
How to read the score
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: PRBench-Legal - professional reasoning benchmark for legal domain. Evaluated using gemini-3.1-pro-preview.
Frequently asked questions
What is the PRBench-Legal benchmark?
PRBench-Legal is a benchmark for broad everyday usefulness across domains. The official description says: 'PRBench-Legal - professional reasoning benchmark for legal domain'. Below we describe in simple words what benchmarks of this type generally examine.
What does PRBench-Legal test?
PRBench-Legal mainly measures broad everyday usefulness across domains. Concretely, it checks: realistic, open-ended requests from varied professional fields; correct, well-structured and helpful responses; consistent quality across very different task types.
How is the PRBench-Legal score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Where do I get PRBench-Legal data and scores?
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/prbench-legal/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Model scores 1 model tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
Qwen3.8-2.4T-A95B
Qwen
|
57.6%
|
18.08.2026 | Report | Verified |