MiMo-V2-Flash

Name: MiMo-V2-Flash
Author: Xiaomi

Xiaomi

MiMo V2 Flash is a fast, lightweight variant of Xiaomi's MiMo V2 language model, optimized for speed and efficiency. It maintains competitive reasoning and coding performance at significantly reduced latency, suitable for real-time applications.

Key Specifications

Parameters

309.0B

Context

Release Date

December 15, 2025

Average Score

66.3%

API Documentation Model Weights Results Blog

Timeline

Key dates in the model's history

Announcement

December 15, 2025

Last Update

January 29, 2026

Today

October 5, 2026

Technical Specifications

Parameters

309.0B

Training Tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests

SWE-Bench Verified

Self-reported by the model provider • Self-reported

73.4%

Reasoning

Logical reasoning and analysis

GPQA

Accuracy • Self-reported

84.0%

Other Tests

Specialized benchmarks

AIME 2025

Accuracy • Self-reported

94.0%

Arena-Hard v2

Standard evaluation • Self-reported

86.0%

MMLU-Pro

Accuracy • Self-reported

85.0%

HMMT 2025

2025 • Self-reported

84.0%

LiveCodeBench v6

Accuracy • Self-reported

81.0%

BrowseComp

With Context Management • Self-reported

58.3%

Humanity's Last Exam

Self-reported by the model provider • Self-reported

22.1%

LongBench v2

Self-reported by the model provider • Self-reported

60.6%

MRCR

Self-reported by the model provider • Self-reported

45.7%

SWE-bench Multilingual

Self-reported by the model provider • Self-reported

71.7%

Tau-bench

Average (τ²-Bench) • Self-reported

80.3%

Terminal-Bench

Hard subset • Self-reported

30.5%

Terminal-Bench 2.0

2.0 • Self-reported

38.5%

License & Metadata

License

mit

Announcement Date

December 15, 2025

Last Updated

January 29, 2026

Similar Models

All Models

MiMo-V2.5-Pro

Xiaomi

1.0T

Best score:1.0 (ARC)

Released:Apr 2026

Price:$0.43/1M tokens

LongCat-Flash-Thinking-2601

Meituan

560.0B

Best score:1.0 (TAU)

Released:Jan 2026

Hy3

Tencent

295.0B

Best score:0.9 (GPQA)

Released:Jul 2026

Mistral Large 2

Mistral AI

123.0B

Best score:0.9 (HumanEval)

Released:Jul 2024

Price:$2.00/1M tokens

LongCat-Flash-Thinking

Meituan

560.0B

Best score:0.8 (TAU)

Released:Sep 2025

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA

253.0B

Best score:0.8 (GPQA)

Released:Apr 2025

Llama 3.1 405B Instruct

LongCat-Flash-Chat

Meituan

560.0B

Best score:0.9 (MMLU)

Released:Aug 2025

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.