Skip to main content

MiniMax M2.5 vs MiMo V2 Flash: Flower Animation on CanopyWave

MiniMax M2.5 vs MiMo V2 Flash: Flower Animation on CanopyWave

The most elaborate output versus the most compact. But only one follows the prompt.

bots.so

The biggest and smallest outputs in this benchmark set. MiniMax produces 4,161 tokens. MiMo produces 2,119. The prompt asked for a looping animation — let’s see who delivered.


Prompt

“Create a gorgeous flower growing from brown dirt, as an animated loop using only HTML and CSS.”

Pure HTML/CSS · No JavaScript · Single file

MiniMax M2.5 CanopyWave
Tokens
4,161
Lines of Code
368
MiMo V2 Flash CanopyWave
Tokens
2,119
Lines of Code
234

Model A

MiniMax M2.5

CanopyWave

vs

Model B

MiMo V2 Flash

CanopyWave

4,161
Tokens
2,119
368
Lines of Code
234

Green highlights the leading metric per row. Fewer tokens = more efficient. More lines = more detail.


Did they loop?

MiniMax M2.5 — Yes. Every animation runs infinite on a synchronized 8-second cycle. It even includes a chain-of-thought reasoning block where the model explicitly plans the looping architecture before writing code. The grow-bloom-fade-reset cycle works cleanly.

MiMo V2 Flash — No. Growth animations use forwards (one-shot). The dirt pops, stem grows, petals appear — then stop. Only a petal wiggle and gentle sway continue looping. The flower doesn’t regrow.

Prompt checklist

RequirementMiniMax M2.5MiMo V2 Flash
FlowerYes — 8 petals, sun, particlesYes — 4 petals, gold center
Brown dirtYesYes — with bounce entrance
Growing animationYesYes
LoopYes — full infinite cycleNo — one-shot, then idle
CSS onlyYesYes

Verdict

MiniMax follows the prompt despite being the most verbose model in the set. MiMo delivers a clean result but skips the loop. Twice the tokens, but it actually does what was asked.


Part of our Model Animation Benchmark series on CanopyWave. Subscribe for new comparisons.

Newsletter

Get the signal, skip the noise.

Weekly digest of new models and provider updates across 40+ compute providers. Curated for AI builders who ship.

New model releases
Capability updates
Provider status
bots.so
The AI Inference Model Index
© bots.so — The AI Inference Model Index

bots.so aggregates publicly available model deployment information from official provider sources. We are not affiliated with any model provider. Model availability changes rapidly; always verify on official sites.