Xiaomi model benchmarks.

Compare Xiaomi models across answer quality, coding, complex tasks, speed, price, and context size.

Xiaomi

Quality

Highest overall scores

  1. 1Xiaomi: MiMo-V2.5-Pro42.9
  2. 2Xiaomi: MiMo-V2.538

Response speed

Fastest output in this sample

  1. 1Xiaomi: MiMo-V2.570 t/s
  2. 2Xiaomi: MiMo-V2.5-Pro28 t/s

Input price

Lowest price per 1M tokens

  1. 1Xiaomi: MiMo-V2.5$0.14/1M
  2. 2Xiaomi: MiMo-V2.5-Pro$0.43/1M

Highlights

Quality

Overall capability · Higher is better

Speed

Output tokens per second · Higher is better

Input price

USD per 1M tokens · Lower is better

Quality benchmarks

Compare Xiaomi model capability.

Performance and price

Compare practical tradeoffs.

All Xiaomi models.

2 models in the current catalogue.

ModelLinks
Xiaomi: MiMo-V2.5-Pro42.928 t/s1.1M$0.43$0.87
Boring technical details Creator of the model
Xiaomi: MiMo-V2.53870 t/s1.1M$0.14$0.28
Boring technical details Creator of the model

Xiaomi technical benchmarks.

Compare named evaluation records available for Xiaomi models. Missing results remain blank rather than being estimated.

BenchmarkAreaMiMo-V2.5-ProMiMo-V2.5Source
Intelligence IndexoverallQuality42.938OpenRouter / artificial-analysis
Coding Indexcoding60.256.8OpenRouter / artificial-analysis
Agentic Indexagentic29.524.4OpenRouter / artificial-analysis
GPQAGPQA Diamond—84.9OpenRouter model benchmarks
Humanity's Last ExamHLE—27.2OpenRouter model benchmarks
IFBenchIFBench—67.1OpenRouter model benchmarks
τ²-Bench Telecomτ²-Bench Telecom—90.6OpenRouter model benchmarks
AA-LCRAA-LCR—68.3OpenRouter model benchmarks
GDPval-AAGDPval-AA—32.5OpenRouter model benchmarks
CritPtCritPt—3.7OpenRouter model benchmarks
SciCodeSciCode—43.1OpenRouter model benchmarks
Terminal-Bench HardTerminal-Bench Hard—41.7OpenRouter model benchmarks
AA-Omniscience AccuracyAA-Omniscience Accuracy—16.8OpenRouter model benchmarks
AA-Omniscience Non-Hallucination RateAA-Omniscience Non-Hallucination Rate—68.1OpenRouter model benchmarks