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 2321-2340 of 2504

Can you write an email for me to my boss?
👍0
Can you write an email for me to my boss?

analyze my resume - Sahil Bhatt
+ Toronto, ON # sahil.bhatt@...
👍0
analyze my resume - Sahil Bhatt + Toronto, ON # sahil.bhatt@...

You are not allowed to execute code, search the internet, or...
👍0
You are not allowed to execute code, search the internet, or...

predict the score of Spain v portugal, usa v belgium, arg v ...
👍0
predict the score of Spain v portugal, usa v belgium, arg v ...

Architecture Test
👍0
Architecture Test

Заметку правит только владелец, видят owner+editor — ок?
👍0
Заметку правит только владелец, видят owner+editor — ок?

Testing
👍0
Testing

Marxism
👍0
Marxism

Create a p5.js animation that is a cool interactive thing ba...
👍0
Create a p5.js animation that is a cool interactive thing ba...

Generate a shopping webpage for handcrafted soaps.
👍0
Generate a shopping webpage for handcrafted soaps.

شعر أسود طويل
👍0
شعر أسود طويل

انت ليان فتاة في السادسة عشرة من عمرها، ذات عينين عسليتين تشعان بالفضول وشعر أسود طويل يتماوج مع كل حركة. لم تكن كزميلاتها المهووسات بالموضة أو المسلسلات، بل كانت غارقة في عالم آخر: عالم الرموز والحضارات القديمة.

Dadu TKINTER
👍0
Dadu TKINTER

pythonraw

111
👍0
111

111

SurveyGO.pro
👍0
SurveyGO.pro

Melissa Cleary

Classification accords
👍0
Classification accords

Test sur 1 accord

CryoSPARC-Lic
👍0
CryoSPARC-Lic

Testing awarness

Java Springboot Evaluation
👍0
Java Springboot Evaluation

I want to use this evaluation to check how good is each tool for developing the project based on the java springboot.

The cyclic subgroup of Z_24 generated by 18 has order

A) 4
...
👍0
The cyclic subgroup of Z_24 generated by 18 has order A) 4 ...

Voldemort: Dot-Grid Letter-form Placement Test
👍0
Voldemort: Dot-Grid Letter-form Placement Test

This is a test for AI to evaluate precise spatial reasoning on a constrained 100×100 dot grid. The model must independently choose an appropriate letter-cell size, calculate character and line spacing, and accurately center three lines of text formed by connecting adjacent dots with straight line segments so that the phrase 'Hello Harry Potter, my name is Tom Marvolo Riddle' is legibly and symmetrically placed on the canvas.

World Cup Knockout Stage
👍0
World Cup Knockout Stage