Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free trial
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Demos
  • 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)

AI Model Benchmarks

Benchmarks measured on real production inference, and the outputs behind every score. Every score has a receipt.

Trap Rate

Questions a child answers and a frontier model can miss.

DeepSeekMiniMaxMoonshotAINVIDIAQwenxAI+1
26 items10 models measuredmeasured 1mo agopublic questions
Trick Riddles

Famous riddles with the twist removed.

DeepSeekMiniMaxMoonshotAINVIDIAQwenxAI+1
24 items10 models measuredmeasured 1mo agopublic questions
Constraint Gauntlet

Follow the instruction exactly. Verified by counting.

DeepSeekMiniMaxMoonshotAINVIDIAQwenxAI+1
28 items10 models measuredmeasured 1mo agopublic questions
Dice Roller

Ask for a random number 50 times. Watch what happens.

AnthropicDeepSeekMetaMiniMaxMoonshotAINVIDIA+3
6 items18 models measuredmeasured 1mo agopublic questions
SVG Gauntlet

Draw a pelican on a bicycle. With code. No looking.

AnthropicDeepSeekGoogleMetaMiniMaxMoonshotAI+6
12 items21 models measuredmeasured 1mo agopublic questions
Calibration

Does the model know when it's right?

DeepSeekMiniMaxMoonshotAINVIDIAQwenxAI+1
50 items10 models measuredmeasured 1mo agopublic questions
Cognitive Reflection

The intuitive answer is wrong. Does the model stop and think?

6 itemsMeasurement runs pendingpublic questions