MicroEvals

Run your prompts across multiple models to compare their performance.
History

Models

Prompt

Examples

Multiple-choice questions across 57 academic and professional subjects 

Loading questions…

Public evaluations

Showing 81-100 of 2488

Candle test
👍1
Candle test

recreate the entire list of characters from the three body p...
👍1
recreate the entire list of characters from the three body p...

Interactive Financial Report
👍1
Interactive Financial Report

Search and mixing topics with diferent lenguajes
👍1
Search and mixing topics with diferent lenguajes

Generate a one paragraph length output that breaks down how ...
👍1
Generate a one paragraph length output that breaks down how ...

Linux Bash Terminal Simulator
👍1
Linux Bash Terminal Simulator

Evaluates models' ability to build a functional Linux bash session simulator

👍1
Greatest retro games

building a versions of the greatest old retro video games of all time

sm2签名分析
👍1
sm2签名分析

sm2签名漏洞分析

England's waterways
👍1
England's waterways

Mapping england's waterways

https://cdn.jsdelivr.net/npm/p5@1.6.0/lib/p5.min.js
👍1
https://cdn.jsdelivr.net/npm/p5@1.6.0/lib/p5.min.js

can open router be used in Codex and Claude Code?
👍1
can open router be used in Codex and Claude Code?

解决望文生义类文字类谜题
👍1
解决望文生义类文字类谜题

经典的文字谜题，考验LLM在文字理解方面程度

test
👍1
test

giii
👍1
giii

You can use a passkey to verify it's really you. Your devic...
👍1
You can use a passkey to verify it's really you. Your devic...

Cipher Bench 1 (Caesar)
👍1
Cipher Bench 1 (Caesar)

0~9→23
👍1
0~9→23

Designing a 1M+ RPS Write-Heavy API Platform in Go
👍1
Designing a 1M+ RPS Write-Heavy API Platform in Go

Jan
👍1
Jan

ETHID
👍1
ETHID

ETHSTORY