MiMo-V2.6-Flash

Tool callingStructured outputReasoningImage inputAudio inputVideo input

Hugging Face Launch post Website

MiMo Flash model for multimodal coding agents and long-context automation

Context: 1.1M
Released: 3w ago
Parameters: —
Input / 1M tokens: $0.14
Output / 1M tokens: $0.28
Cached input / 1M tokens: $0.0028

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Xiaomi
Model family: MiMo
Type: Language model
Predecessor: —
Successor: —
Released: September 22, 2026
Model ID: xiaomi/mimo-v2.6-flash
Openness: Open weights
License: —
Parameters: —
Input modalities: text, image, video, audio
Output modalities: text
Modality: text+image+audio+video->text
Tokenizer: Other
Max output tokens: 131K
Hugging Face: XiaomiMiMo/MiMo-V2.6-Flash-RL
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: xiaomi/mimo-v2.6-flash
Source family: mimo
Last updated: 2026-09-22
Model context: 1.0M
Model output limit: 131K
Open weights: Yes
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
DeepSWE	67.9 · score	1.1	Source
ProgramBench	26 · score	—	Source
MiMo Code Bench	61.2 · score	—	Source
AutomationBench	52.3 · score	1.0.6	Source
Toolathlon-Verified	73.6 · score	—	Source
Agents' Last Exam	27.6 · score	—	Source
Terminal-Bench	28.8 · score	4.0	Source
Terminal-Bench	87.6 · score	2.1	Source
OSWorld-Verified	80.8 · score	—	Source
JobBench	61.2 · score	—	Source
CyberGym	95.1 · score	—	Source
MiMo Cyber Bench	77.2 · score	—	Source
ExploitGym	6 · score	—	Source
ExploitBench	25.3 · score	—	Source
SEC-Bench Pro	47.5 · score	—	Source
MiMo VisualCoding	71.5 · score	—	Source

Complete source record (JSON)

{
  "id": "xiaomi/mimo-v2.6-flash",
  "name": "MiMo-V2.6-Flash",
  "description": "MiMo Flash model for multimodal coding agents and long-context automation",
  "family": "mimo",
  "last_updated": "2026-09-22",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "audio",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1048576,
    "output": 131072
  },
  "benchmarks": [
    {
      "name": "DeepSWE",
      "score": 67.9,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score",
      "version": "1.1"
    },
    {
      "name": "ProgramBench",
      "score": 26,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "MiMo Code Bench",
      "score": 61.2,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "AutomationBench",
      "score": 52.3,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score",
      "version": "1.0.6"
    },
    {
      "name": "Toolathlon-Verified",
      "score": 73.6,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "Agents' Last Exam",
      "score": 27.6,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "Terminal-Bench",
      "score": 28.8,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score",
      "version": "4.0"
    },
    {
      "name": "Terminal-Bench",
      "score": 87.6,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score",
      "version": "2.1"
    },
    {
      "name": "OSWorld-Verified",
      "score": 80.8,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "JobBench",
      "score": 61.2,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "CyberGym",
      "score": 95.1,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "MiMo Cyber Bench",
      "score": 77.2,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "ExploitGym",
      "score": 6,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "ExploitBench",
      "score": 25.3,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "SEC-Bench Pro",
      "score": 47.5,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    },
    {
      "name": "MiMo VisualCoding",
      "score": 71.5,
      "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "metric": "score"
    }
  ],
  "release_date": "2026-09-22",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Darkbloom	darkbloom/fp4	1.0M	$0.10	$0.28	$0.05	—	95.74%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Makora	makora/fp8	1.0M	$0.13	$0.28	$0.002	—	94.72%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Checked 2026-10-15
DeepInfra	deepinfra/fp8	1.0M	$0.13	$0.27	$0.00266	—	88.53%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
GMICloud	gmicloud/bf16	1.1M	$0.14	$0.28	$0.003	—	45.80%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Novita	novita/fp8	1.0M	$0.14	$0.28	$0.0028	—	98.89%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Xiaomi	xiaomi/fp8	1.0M	$0.14	$0.28	$0.0028	—	99.58%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Io Net	io-net/fp8	1.0M	$0.15	$0.29	$0.02	—	98.74%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Venice	venice/fp8	1M	$0.18	$0.35	$0.00375	—	56.13%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware