MiMo-V2.6-Flash

Released
2026-09-21
Last refreshed
2026-10-29
Status
Researched 23d ago
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool useMultimodal
Xiaomi releases · 10 in the last 12 months · this family litChangelog →
Specifications
Family
MiMo
Released
2026-09-21
Context
1M
Max output
128K
Parameters
309B total / 15B active (MoE)
Specialization
general
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

Consumer electronics and AI research.

Beijing, China
Founded 2010
Website
Pricing
Output / 1M
$0.280
Input / 1M
$0.140

Cheapest of 2 routes · Xiaomi · cache read $0.0028

About

Xiaomi MiMo-V2.6-Flash is Xiaomi MiMo's September 21, 2026 efficiency-balanced open-weights MoE (309B total / 15B active), sibling of MiMo-V2.6-Pro. First-party HF checkpoint XiaomiMiMo/MiMo-V2.6-Flash-RL (MIT; ungated; 1M context) is the released Flash RL weights; product/API id is mimo-v2.6-flash. First-party news: the series comprises two native fully multimodal models (Pro and Flash); Flash comprehensively outperformed MiMo-V2.5-Pro. Product card: full-modality high-intelligence low-cost reasoning for high-frequency and large-scale professional workflows; context 1M; max output 128K; input text, image, video, and audio. Overseas API pricing (pay-as-you-go): $0.0028 cache-hit / $0.14 cache-miss input and $0.28 output per 1M tokens; batch $0.0014 / $0.07 / $0.14.

Providers(2)

Compare all 2

Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
Xiaomi$0.140$0.280$0.070 / $0.140read $0.0028
Serverless
OpenRouter$0.140$0.280-read $0.0028
Serverless

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt CachingBatch APIAudioVideo

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(14)

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.
BenchmarkScoreVersionEvaluationSource
67.9DeepSWE v1.1Observed 2026-10-09—
26.0ProgramBenchObserved 2026-10-09—
52.3AutomationBench v1.0.6Observed 2026-10-09—
73.6Toolathlon-VerifiedObserved 2026-10-09—
27.6Agents' Last ExamObserved 2026-10-09—
28.8Terminal Bench 4.0Observed 2026-10-09—
87.6Terminal Bench 2.1Observed 2026-10-09—
80.8OSWorld-VerifiedObserved 2026-10-09—
95.1CyberGymObserved 2026-10-09—
6.0ExploitGymObserved 2026-10-09—
47.5SEC Bench ProObserved 2026-10-09—
1448.0text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26
Configuration: MiMo-V2.6-Flash
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'MiMo-V2.6-Flash': rank 81, Arena Score 1448.1 (95% CI 1442.1-1454.1), 13730 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1244.0vision_style_control overall 2026-10-19 (style control, default view)Observed 2026-10-26
Configuration: MiMo-V2.6-Flash
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena vision style control leaderboard, overall category, published 2026-10-19 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'MiMo-V2.6-Flash': rank 61, Arena Score 1244.5 (95% CI 1233.6-1255.4), 3618 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1404.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: MiMo-V2.6-Flash
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.6-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 87 of 416, rating 1404.3 (95% CI 1392.1-1416.4), 2741 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

API versions

MiMo-V2.6-Flashmimo-v2.6-flashXiaomiMiMo/MiMo-V2.6-Flash-RLMiMo-V2.6-Flash-RLXiaomi MiMo-V2.6-Flash