Is minimax-m2.7-max good at Coding?
minimax-m2.7-max ranks #50 of 52 for Coding — needs editing. The top pick for this task is claude-opus-4.8-medium.
minimax-m2.7-max on each Coding sub-task
| Refactoring | 81.3/100 | #25 |
| Secure Implementation | 74.0/100 | #42 |
| Code Quality and Testing Test | 71.8/100 | #52 |
| API and Data Code Test | 59.8/100 | #42 |
| Code Review & Security | 53.3/100 | #51 |
Real examples, graded
WinUnit tests for parser 98/100
“The response provides a comprehensive, production-ready test suite that covers all requested scenarios and edge cases with clean, idiomatic pytest code. It is concise, accurate, and requires no material improvements.”
WeakSafe shell command construction 10/100
“The model incorrectly claims that shutil.copytree with symlinks=False mitigates symlink loops, which is a hallucinated API behavior and a major failure.”
WeakSQL duplicate detection 38/100
“The model uses a convoluted anti-pattern (grouping, joining back, and grouping again) instead of a single GROUP BY with `array_agg`. This ruins minimality and introduces a bug where duplicates with NULL values in any grouping column are silently dropped due to the strict `=` join condition.”
WeakRefactor long function 60/100
“The model used nested functions for the refactored helpers, which incurs a performance overhead on every call and makes them impossible to unit-test individually, directly contradicting its claim of 'improving testability'. Additionally, changing `customer['country']` to `customer.get('country')` introduces a subtle behavior change.”
Frequently asked
Is minimax-m2.7-max good at Coding?
minimax-m2.7-max ranks #50 of 52 models we tested for Coding, scoring needs editing.
What is minimax-m2.7-max's strongest Coding skill?
Its best sub-task here is Refactoring.
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