General Capabilities Benchmark

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.

Model scores 1 model tested

Reset
# Model Score Date Source Verified
1 Qwen3.8-2.4T-A95B
Qwen
57.6%
18.08.2026 Report Verified

What now?

You've seen how models score on PRBench-Legal — here's what to do next.