Short answer: MiMo V2.5 is 35x cheaper (0.018¢ vs 0.63¢ a chat). OpenAI o3 ranks higher overall (#5 vs #10). OpenAI o3 wins at coding, following instructions, agentic tasks. Pick MiMo V2.5 for everyday use and OpenAI o3 when quality matters most.
OOPENAIGANG
OPENAI O3
OPENAI GANG
CRAPGPT.LOLINDEPENDENT AI MODEL REVIEWS
CRAP SCORE672 SOURCES
INTELLIGENCEPEOPLETOOLSA BRIGHTERTOMORROW.
BETTERIDEASHIGHERPEOPLE
POWER82AA · CRAPGPT
Math
89
Code
83
Instruction
79
Reasoning
73
Agentic
71
Value
38
LIEUTENANT★★★★
ANALYST / CODER
0.63¢ per chat · 159 chats per NZ$1
“Show your working.”
Every model is somebody.
— CRAPGPT.LOL —
XXIAOMIGANG
MIMO V2.5
XIAOMI GANG
CRAPGPT.LOLINDEPENDENT AI MODEL REVIEWS
CRAP SCORE722 SOURCES
MOREFORLESS
FASTCHEAPSMART
POWER67AA · CRAPGPT
Writing
90
Instruction
74
Reasoning
73
Code
62
Agentic
55
Value
82
RUNNER★★★★
GENERALIST / WRITER
0.018¢ per chat · 5,549 chats per NZ$1
“Faster than your bottleneck.”
Every model is somebody.
— CRAPGPT.LOL —
OpenAI o3
MiMo V2.5
Cost per chat (NZD)
0.63¢
0.018¢
Chats per NZ$1
159
5,549
Overall rank
#5
#10
Vendor
OpenAI
Xiaomi
Speciality
Math
General
Crowd Elo
no votes
1000
Reasoning
73
73
Code
83
62
Instruction
79
74
Agentic
71
55
Scores are 0 to 100 percentiles blending LMArena, Epoch AI, Artificial Analysis and CrapGPT's own tests. Updated 2026-10-13.
FAQ
Which is cheaper, OpenAI o3 or MiMo V2.5?
MiMo V2.5 costs 0.018¢ per typical chat versus 0.63¢ for OpenAI o3 on CrapGPT (NZD, measured token use).
Which is better, OpenAI o3 or MiMo V2.5?
OpenAI o3 ranks higher overall on CrapGPT's blended benchmark score. By category: OpenAI o3 leads at coding, following instructions, agentic tasks.
Can I try OpenAI o3 and MiMo V2.5 side by side?
Yes. CrapGPT's card battle sends one prompt to two models and lets you pick the winner, paying only for the two replies.
