Xiaomi MiMo-V2.5-Pro

Name: Xiaomi MiMo-V2.5-Pro
Author: Xiaomi

Released

2026-04-22

Last refreshed

2026-06-29

Status

Researched 101d ago

ProprietaryCommercial use: conditionalCodingRAGAgentsLong contextClassificationJSON / Tool useCodingAgentLong Context

Xiaomi MiMo-V2.5-Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

Teams evaluating coding, rag, and agents
Workloads that can use a 1.05m context window
Buyers comparing 3 tracked provider routes

Do not use it for

Vision or document-understanding workloads

Specifications

Family: MiMo
Released: 2026-04-22
Context: 1.05m
Parameters: 1T
Architecture: Mixture of Experts
Specialization: code
Openness: Proprietary
License: ProprietaryCommercial use: conditional
Weights: Not released
Code: Unknown
Training: Pretrained

Created by

Xiaomi

Consumer electronics and AI research.

Beijing, China

Founded 2010

Website

Pricing

Output / 1M

$0.870

Input / 1M

$0.435

Cheapest of 3 routes · OpenRouter

Providers(3)

OpenRouter Xiaomi Novita AI

View 3 provider routes

Links

Website

About

Xiaomi's April 22, 2026 public-beta flagship in the MiMo-V2.5 series. The official Xiaomi MiMo page describes MiMo-V2.5-Pro as its most capable model to date, focused on general agentic capability, complex software engineering, long-horizon tasks, and ultra-long-context instruction following. OpenRouter lists it as text-to-text with 1,048,576 token context, 131,072 max completion tokens, reasoning controls, tool use, and response_format support. Xiaomi says the V2.5 series will be open-sourced soon, but no public weights/license were verified at research time.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ B

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Cache	Route
OpenRouter	$0.435	$0.870	-	Serverless
Xiaomi	$0.435	$0.870	read $0.0036	Serverless
Novita AI	$2.00	$6.00	read $0.400	Serverless

Capabilities

JSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

SWE-bench ProRank 21 of 46

80.3

79.2

69.2

67.7

Xiaomi MiMo-V2.5-Procurrent

57.2

SWE-bench VerifiedRank 21 of 81

Claude Fable 5

96.0

Claude Opus 5

96.0

Claude Mythos Preview

93.9

Claude Opus 4.8

88.6

Xiaomi MiMo-V2.5-Procurrent

78.9

Benchmark scores(7)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.

Benchmark	Score	Version	Evaluation	Source
Massive Multitask Language Understanding	89.4	—Observed 2026-04-28	—	Source
MMLU PRO	68.5	—Observed 2026-04-28	—	Source
Google-Proof Q&A	66.7	diamondObserved 2026-04-28	—	Source
SWE-bench Verified	78.9	SWE-Bench Verified (Resolved)Observed 2026-04-28	—	Source
SWE-bench Pro	57.2	SWE-bench Pro (resolved%)Observed 2026-06-07	—	Source
Terminal-Bench 2.0	68.4	Terminal-Bench 2.0 (score)Observed 2026-06-07	—	Source
GeneBench-Pro	2.0	xhighObserved 2026-06-30	—	Source