Skip to main content
AITier

MiMo-V2.5-Pro

XiaomiOpen WeightMIT · Commercial OK

Description

MiMo-V2.5-Pro is Xiaomi's 1.02T-parameter sparse Mixture-of-Experts language model with 42B active parameters and a 1M-token context window. It inherits the MiMo-V2-Flash hybrid-attention and Multi-Token Prediction design, extends context during pre-training up to 1M tokens, and uses supervised fine-tuning, domain-specialized reinforcement learning, and Multi-Teacher On-Policy Distillation to improve complex software engineering, long-horizon agentic tasks, and ultra-long-context coherence.

Release Date
2026-04-22
Parameters
1.0T
Context Length
1.0M
Modalities
text

Capability Radar

41
general
59
coding
87
reasoning
64
science
70
agents
0
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability52
52.0
LS
Code Ranking64
78.0
AA
General Ranking41
81.0
AA
Science56
79.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

FrontierSWE (Impl.)340.0%SR
MiMo Coding Bench73.7%SR
TAU3-Bench72.9%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)68.4%SR
Claw-Eval64.0%SR
SWE-Bench ProPrinceton NLP (2024)57.2%SR
WildClawBench43.0%SR
Finance Agent v241.5%

Biology

GPQANYU + Cohere + Anthropic (2023)66.7%SR

Code

SWE-Bench Verified78.9%SR

Finance

MMLU89.4%SR
MMLU-Pro68.5%SR

General

ARC-C97.2%SR
MMLU-Redux92.8%SR
C-Eval91.5%SR
CMMLU90.2%SR
Global-MMLU83.6%SR
TriviaQA81.3%SR
MBPP+74.1%SR
LiveCodeBench v639.6%SR
SWE-bench Verified (Agentless)35.7%SR

Language

BBH88.4%SR
Winogrande85.6%SR

Long Context

GraphWalks62.0%SR

Math

GSM8k99.6%SR
DROP86.3%SR
MATH86.2%SR
AIMEMAA37.3%SR
Humanity's Last Exam34.0%SR

Reasoning

HellaSwagAI2 (2019)89.8%SR
HumanEval+75.6%SR

AA Evaluation Indices

(Artificial Analysis)
Coding Index(Artificial Analysis)
60.2
Intelligence Index(Artificial Analysis)
42.9
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Ifbench(Google Research (2023))
0.8
Lcr(Artificial Analysis)
0.8
Terminalbench V2 1
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.5
Terminalbench Hard(Stanford × Laude Institute (2026))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.4
Tau Banking
0.1

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
90
Legal
80
Math
80
Reasoning
80
Frontend Development
80
Healthcare
80
Physics
70
Finance
70
General
70
Biology
70
Chemistry
70
Code
70
Tool Calling
70
Long Context
60
Agents
60
Coding
40
Vision
30

Pricing

Input Price$0.435 / 1M tokens
Output Price$0.87 / 1M tokens
Blended Price (3:1)$0.544 / 1M tokens
Cache Read Price$0.0036 / 1M tokens

Speed

Tokens/sec48.1
Time to First Token2.82s
Time to Answer44.40s

Provider Price Ranking

Provider Price Ranking

8 providers

Cheapest: XiaomiMost Expensive: EmpirioLabs AI
ProviderInputOutput
1XiaomiCheapest
$0
$0
2DeepInfra
$0
$0
3Novita
$0
$0.00001
4DigitalOcean
$0.4
$1.5
5CrofAI
$0.4
$0.8
6OpenCode Go
$0.435
$0.87
7LLM Gateway
$0.435
$0.87
8EmpirioLabs AI
$2.175
$4.35

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis