Compare MiniMax: MiniMax M2.1 by MiniMax against Claude Sonnet 4 by Anthropic, tested across 33 shared challenges. Updated February 2026.
33 challenges
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Each brother sees 2 sisters. Since Sally herself is one of those sisters, there is exactly one other sister besides Sally.
Answer: Sally has 1 sister.
I need to think through this step-by-step.
Given information:
Let me work out how many sisters are in the family total.
If each of Sally's 3 brothers has 2 sisters, and all the brothers are in the same family, then there must be 2 sisters total in the family.
Since Sally is one of those sisters, and there are 2 sisters total, Sally must have 1 sister.
Therefore, Sally has 1 sister.
Tests an AI's understanding of number representation
No, 9.11 is not greater than 9.9.
In fact, 9.11 is less than 9.9.
Here's why: When comparing decimals, you look at the place values from left to right. Both numbers have the same value in the ones place (9). However, in the tenths place, 9.11 has a 1 while 9.9 has a 9. Since 1 < 9, 9.11 is the smaller number.
To make the comparison clearer, you can also write them with the same number of decimal places:
Now it's easier to see that 11 hundredths is less than 90 hundredths.
Tests an AI's randomness and creativity
Here are five original jokes:
Why did the scarecrow become a stand‑up comedian?
Because he was great at delivering dead‑pan punchlines!
I told my computer I needed a break, and it said “No problem — I’ll go to sleep mode.”
Why don’t skeletons fight each other?
They don’t have the guts.
I asked the librarian if the library had any books on paranoia.
She whispered, “They’re right behind you.”
How does a penguin build its house?
Igloos it together.
All five jokes are unique.
Here are 5 jokes for you:
Why don't scientists trust atoms? Because they make up everything!
I told my wife she was drawing her eyebrows too high. She looked surprised.
Why don't eggs tell jokes? They'd crack each other up!
I'm reading a book about anti-gravity. It's impossible to put down!
Why did the scarecrow win an award? He was outstanding in his field!
All 5 jokes are unique - each one has a different setup, punchline, and comedic concept. They cover different types of wordplay: scientific puns (#1, #4), visual humor (#2), food puns (#3), and agricultural wordplay (#5).
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Recreate an interactive, classic Mario level in a single HTML file.
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Tests an AI's ability to create interactive web elements
Tests an AI's ability to create a detailed world map in SVG format
Generate a single-page, self-contained HTML webapp using Tailwind CSS for a randomly chosen category/industry/niche.
