Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
All skills
Code

Write an eval suite

Runnable tasks that measure a capability, with a scored report at the end.

Fill it in

The specific thing you suspect is weak.

How many cases.

How a run is scored.

Your prompt

Build an eval suite of 15 tasks, graded by A mix.

What to measure: [your what to measure]

Write tasks that can FAIL. The most common mistake in an eval suite is tasks the
subject passes trivially, which produces a 95% score that measures nothing. Aim
for a spread: if everything passes, the suite is too easy and you have learned
nothing.

Each task needs an unambiguous expected outcome and a grader that cannot be
argued with. Where a rubric is unavoidable, write the rubric as checks rather
than adjectives.

Run it, report the score with per-task results, and be specific about what the
failures have in common. That pattern is the actual output; the number is just
the headline.
Use Write an eval suiteOpens with everything above already filled in.

Why this works

The usual failure is tasks the subject passes trivially, producing a 95% that measures nothing. This aims for a spread, writes graders that cannot be argued with, runs the suite, and reports what the failures have in common. That pattern is the output; the score is just the headline.

Questions

Can it evaluate any model?
The suite is runnable code, so point it at whatever you like.

More code skills

  • idapt Code
  • Fix a failing test

Use it now in a chat in 1 click

Use Write an eval suite
Fix a GitHub issue
  • Find security bugs
  • Ship a feature
  • Speed up slow code