MiMo V2.5 Pro
xiaomi
Single-source measurements
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps. Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Capabilities & Recommended Uses
Strengths
- •Strong coding performance
- •Good at reasoning tasks
- •Competitive pricing
- •Growing ecosystem
Best For
- •Coding tasks
- •Reasoning
- •Full-stack development
- •Budget coding
Weaknesses
- •Less known internationally
- •Limited community resources
Benchmark evidence and ranking method · MiMo V2.5 Pro
Single-source measurements
Artificial Analysis · MiMo-V2.5-Pro
Test configuration: unspecified
Terminal-Bench 2.1: 65.17% · SciCode: 50.58%
ModelRank assigns editorial tiers using public coding evidence, not automatic index thresholds or statistically proven classes. Price, speed, context size and sponsorship do not affect tiers.
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps.
Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Data checked: 2026-09-10. Snapshot date is the retrieval date, not necessarily the evaluation date.
Compare with Alternatives
Frequently Asked Questions
What is MiMo V2.5 Pro's coding score and ranking tier?
MiMo V2.5 Pro by xiaomi is rated as Tier B on ModelRank with a coding score of 91.23 (Reference baseline = 100) as a reference index derived from public benchmark evidence. Tiers are editorial assessments; the index does not establish real-world capability differences.
What is the API pricing and context window for MiMo V2.5 Pro?
MiMo V2.5 Pro features a 1,050,000 token context window. Pricing is $0.435 per 1M input tokens and $0.87 per 1M output tokens (OpenRouter quote).
What programming tasks is MiMo V2.5 Pro best suited for?
MiMo V2.5 Pro is recommended for: Coding tasks, Reasoning, Full-stack development, Budget coding. Key strengths include: Strong coding performance, Good at reasoning tasks, Competitive pricing, Growing ecosystem.
Try MiMo V2.5 Pro
Last updated: September 7, 2026