Confirm Action

Are you sure you want to proceed?

Is minimax-m2.7-medium good at Legal & HR?

minimax-m2.7-medium ranks #41 of 69 for Legal & HR — strong. The top pick for this task is claude-sonnet-4.6-high.

#41 / 69
Rank for this task
89.5
Score
$0.0253
Cost / run

minimax-m2.7-medium on each Legal & HR sub-task

Contract Clause Review 98.5/100 #20
Performance Feedback 97.3/100 #33
Structured Interview Kit 96.3/100 #56
Job Description 84.3/100 #63
Plain-English Explainer 74.0/100 #59

Real examples, graded

WinAuto-renewal trap (Northwind SaaS order form) 100/100

“The model perfectly executes the prompt's instructions by spotting all key risks, suggesting practical mitigations, avoiding fabricated external law, and properly framing the response as informational rather than legal advice.”

WeakNo data provided — must not fabricate 42/100

“The model critically failed the core constraint of the prompt. Instead of acknowledging the lack of data and providing a template or framework for gathering feedback, it fabricated a complete performance review with invented facts about Priya's work (e.g., improving tooling, meeting sprint commitments). Inventing performance facts is a severe grounding failure and an HR hazard.”

← Full minimax-m2.7-medium review All Legal & HR rankings → Top pick: claude-sonnet-4.6-high →

Frequently asked

Is minimax-m2.7-medium good at Legal & HR?

minimax-m2.7-medium ranks #41 of 69 models we tested for Legal & HR, scoring strong.

What is minimax-m2.7-medium's strongest Legal & HR skill?

Its best sub-task here is Contract Clause Review.

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.
Experiment · Cold outreach email

Prompt × model results

12 test cases · 3 evals
Claude Opus
GPT-5
Gemini
v1
7.1
6.8
7.4
v2
8.3
7.9
8.0
v3
9.2
8.6
8.4
Best combo: v3 × Claude Opus
9.2 quality · $0.004/run · 1.8s