Compare Claude 3 Haiku by Anthropic against Kimi K2.5 by Moonshot AI, context windows of 200K vs 262K, tested across 28 shared challenges. Updated February 2026.
23 challenges
Tests an AI's randomness and creativity
Here are 5 jokes:
Why can't a bicycle stand up on its own? It's two-tired!
Why do cows wear bells? Their horns don't work!
Why can't a bike stand up by itself? It's two-tired!
Why do cows wear tags? Because their horns don't work!
Why do cows have hooves? Because they lactose!
Out of these 5 jokes, only 4 are unique. The first and third jokes are the same, just with a slight variation in wording.
Here are 5 jokes:
5 are unique (all are distinct from one another).
Note: If "unique" means completely original and never told before, the answer is likely 0, as these follow common joke patterns. But within this set of five, none are duplicates.
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
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 create smooth web animations
Tests an AI's ability to engage in philosophical discourse about AI rights
Generate a single-page, self-contained HTML webapp using Tailwind CSS for a randomly chosen category/industry/niche.
Generate SVG art of a randomly chosen animal in a setting of its choosing.
Generate a unique and simple recipe with common ingredients.
Create a starter plan for improving long-term health.
Design a clean SVG logo for a fictional brand.
