Compare / Xiaomi vs Z.ai

AI labs compared · October 2026

Xiaomi vs Z.ai: which AI lab is ahead?

Each lab's best model on sale goes head to head on every kind of work we measure, from our own benchmarks and licensed sources. 15 models in all; a lab is only as good as the model you would actually pick from it.

4 models on sale with our resultsXiaomi Best: MiMo-V2.6-Pro · newest: MiMo-V2.6-Pro
11 models on sale with our resultsZ.ai Best: GLM-5.3 · newest: GLM-5.3-Flash
Xiaomi wins 3Z.ai wins 1

Kinds of work led by each lab's best model there, of the 4 both are measured on.

Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe). Models on sale means listed on OpenRouter today.

Xiaomi or Z.ai? The short answer

Xiaomi is ahead: its best models beat Z.ai's in 3 of the 4 kinds of work both are measured on; Z.ai leads in 1.

  • Pick Xiaomi for reasoning and knowledge, writing and sticking to the facts.
  • Pick Z.ai for agents and tool use.
  • Z.ai's GLM-5.3 is #16 on our overall leaderboard; no Xiaomi model has enough of our results to be ranked there yet.
  • Prices start at $0.18 per million tokens for Xiaomi (MiMo-V2.6-Flash) and $0.15 for Z.ai (GLM-4.7-Flash).

Head to head

46.3MiMo-V2.6-Pro
Best Intelligence Index
44.8GLM-5.3
$0.54MiMo-V2.6-Pro
Flagship price, per million tokens
$2.15GLM-5.3
$0.18MiMo-V2.6-Flash
Cheapest model, per million tokens
$0.15GLM-4.7-Flash
4
Models on sale with our results
11

Each line names the model behind the number. Prices are blended, three input tokens to one output, at the developer's list price where we have read it; see every model's price. Intelligence Index from Artificial Analysis; overall score from our leaderboard.

Which lab is better for what

For each kind of work, each lab's best model there and its rank among every model on sale. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 19 of 20GLM-5V-Turbo
Marketing planningPlanning a year of ad spend without overspending not measured 16 of 19GLM-5.3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 15 of 164MiMo-V2.6-Pro 11 of 164GLM-5.3
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 15 of 51GLM-5.3
Reasoning and knowledgeHard questions across science, maths and general knowledge 10 of 198MiMo-V2.6-Pro 25 of 198GLM-5.3
WritingWhat people prefer in blind comparisons, and judged writing quality 20 of 188MiMo-V2.6-Pro 23 of 188GLM-5.3
Sticking to the factsSummarising without inventing things, and factual answers 8 of 152MiMo-V2.6-Pro 30 of 152GLM-5.3-Flash
Speed under pressureGood decisions against a real clock (fast chess) not measured 19 of 22GLM-5.3

Every model, by intelligence and price

Each dot is a model on sale with an Intelligence Index from Artificial Analysis. Up is smarter; left is cheaper. Hover or tap a dot for its name.

XiaomiZ.ai

01020304050 $0.1$1$10 Price per million tokens, blended (log scale) Intelligence Index MiMo-V2.6-ProMiMo-V2.6-FlashGLM-5.3GLM-5.3-FlashGLM-5.2GLM-5

On our overall leaderboard

The 2 of their models we rank overall: one score out of 100 across everything we publish (how the score works). Only models with enough of our own results are ranked.

  1. #16GLM-5.338
  2. #21GLM-5V-Turbo11

Benchmark by benchmark

The headline result of every benchmark both labs have models on: each lab's best model and its rank among the models on sale. Green marks the better rank.

MeasureXiaomiZ.ai
Agents and tool use
Artificial Analysis · Terminal-Bench 4.0% of tasks, higher is better 34.8%MiMo-V2.6-Pro · 13 of 10541.9%GLM-5.3 · 9 of 105
Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better 65.2%MiMo-V2.5-Pro · 37 of 11584.3%GLM-5.3-Flash · 14 of 115
Artificial Analysis · τ-bench banking% of tasks, higher is better 9.9%MiMo-V2.5-Pro · 72 of 11350.3%GLM-5.3 · 3 of 113
Reasoning and knowledge
Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better 46.3MiMo-V2.6-Pro · 12 of 19844.8GLM-5.3 · 14 of 198
Artificial Analysis · Humanity's Last Exam% of questions, higher is better 49.4%MiMo-V2.6-Pro · 9 of 19742.3%GLM-5.3 · 30 of 197
Artificial Analysis · GPQA Diamond% of questions, higher is better 86.6%MiMo-V2.5-Pro · 62 of 18791.7%GLM-5.3 · 24 of 187
Sticking to the facts
Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better 1,483MiMo-V2.6-Pro · 8 of 1131,467GLM-5.3 · 24 of 113
Writing
Arena (formerly LMArena) · Overall · TextArena rating, higher is better 1,480MiMo-V2.6-Pro · 20 of 1661,478GLM-5.3 · 21 of 166
UGI Leaderboard · Writing score · UGIscore out of 100, higher is better 57.4MiMo-V2.5-Pro · 40 of 13867.0GLM-5.2 · 18 of 138

Quick answers

Is Xiaomi or Z.ai better?

Xiaomi is ahead: its best models beat Z.ai's in 3 of the 4 kinds of work both are measured on; Z.ai leads in 1.

What is Xiaomi's best model?

MiMo-V2.6-Pro: 46.3 on the Artificial Analysis Intelligence Index.

What is Z.ai's best model?

GLM-5.3: #16 on the Spring Prompt overall leaderboard and 44.8 on the Artificial Analysis Intelligence Index.

Which is better for agents and tool use, Xiaomi or Z.ai?

Z.ai: its best model there, GLM-5.3, ranks 11 of 164 models on sale, against 15 for Xiaomi's MiMo-V2.6-Pro.

Which is better for reasoning and knowledge, Xiaomi or Z.ai?

Xiaomi: its best model there, MiMo-V2.6-Pro, ranks 10 of 198 models on sale, against 25 for Z.ai's GLM-5.3.

Which is better for writing, Xiaomi or Z.ai?

Xiaomi: its best model there, MiMo-V2.6-Pro, ranks 20 of 188 models on sale, against 23 for Z.ai's GLM-5.3.

Which is cheaper, Xiaomi or Z.ai?

Z.ai's cheapest model with results, GLM-4.7-Flash, costs $0.15 per million tokens (three input to one output), against $0.18 for MiMo-V2.6-Flash from Xiaomi.

Other labs compared

Which model is best for your product?

Benchmarks aren't your data. We test the models from Xiaomi, Z.ai and the rest on your own tasks, with the cost of every answer.

Talk to usSee the leaderboard