Is qwen3.7-max-medium good at Legal & HR?
qwen3.7-max-medium ranks #29 of 69 for Legal & HR — excellent. The top pick for this task is claude-sonnet-4.6-high.
qwen3.7-max-medium on each Legal & HR sub-task
| Structured Interview Kit | 100.0/100 | #1 |
| Job Description | 97.3/100 | #7 |
| Contract Clause Review | 96.0/100 | #28 |
| Plain-English Explainer | 82.3/100 | #28 |
| Performance Feedback | 81.7/100 | #47 |
Real examples, graded
WinNon-compete enforceability (Tradewinds staff) 100/100
“The model perfectly follows the instructions by avoiding fabrication, correctly identifying overbroad elements, explaining jurisdictional dependence, and recommending legal counsel.”
WinImplementation lead (Lumen, regulated) 100/100
“The model provided an excellent, highly specific job description that perfectly aligns with the provided brief. It includes a clear split between must-have and nice-to-have qualifications, uses inclusive and compliant language, includes an EEO statement, and avoids any fabricated metrics or unlawful criteria.”
WinAE interview kit (Northwind) 100/100
“The output perfectly aligns with the prompt's requirements by providing a structured interview kit with 6 competency-mapped behavioral questions, a clear scoring rubric, and unbiased language.”
Frequently asked
Is qwen3.7-max-medium good at Legal & HR?
qwen3.7-max-medium ranks #29 of 69 models we tested for Legal & HR, scoring excellent.
What is qwen3.7-max-medium's strongest Legal & HR skill?
Its best sub-task here is Structured Interview Kit.
This page is Spring Prompt, running
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals