Compare GPT-5.2 Pro by OpenAI against Qwen3 235B A22B by Qwen, context windows of 400K vs 33K, tested across 3 shared challenges. Updated February 2026.
3 challenges
Tests an AI's randomness and creativity
Unique jokes: 5.
Here are 5 jokes I generated:
Why don't skeletons fight each other?
They don't have the guts!
What do you call a fake noodle?
An impasta!
Why did the math book look sad?
Because it had too many problems!
What do you call a fish wearing a bowtie?
Sofishticated!
Why did the programmer quit?
Because he didn't get arrays (a raise)!
How many are unique?
All 5 are unique! While some joke structures (e.g., puns, wordplay) overlap, the topics (skeletons, math, fish, programming) and punchlines are distinct. Even if some ideas are common, they don't repeat within this set. 😄
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Generate SVG art of a randomly chosen animal in a setting of its choosing.
