What is the IQ of mimo-v2.6-flash?

mimo-v2.6-flash has an estimated IQ of 121, which ranks #45 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

What is mimo-v2.6-flash best at?

Among the dimensions with published benchmark results, mimo-v2.6-flash ranks highest in Programmatic Reasoning (IQ 136, #27 of 177) and Mathematical Reasoning (IQ 129, #36 of 176). Its lowest-ranked measured dimension is Reliability (IQ 111, #101 of 177).

What is the EQ of mimo-v2.6-flash?

mimo-v2.6-flash doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for mimo-v2.6-flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has mimo-v2.6-flash been tested on?

mimo-v2.6-flash has published results on 16 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, GDPval-AA v2.1 normalized score, AA-Briefcase v1.1 Elo, ProgramBench and Terminal-Bench 4.0.

How much does mimo-v2.6-flash cost?

mimo-v2.6-flash costs $0.14 per million input tokens and $0.28 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.6897 per million input-plus-output tokens.

Is mimo-v2.6-flash open source?

Yes — mimo-v2.6-flash is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

Who developed mimo-v2.6-flash?

mimo-v2.6-flash was developed by Xiaomi, based in China.

When was mimo-v2.6-flash released?

mimo-v2.6-flash was publicly released on September 22, 2026.

How large is the context window of mimo-v2.6-flash?

mimo-v2.6-flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is mimo-v2.6-flash?

In independent measurements, mimo-v2.6-flash generates about 56 tokens per second, with a typical response time of about 48 seconds.

XiaomiReleased Sep 22, 2026

Open weights

mimo-v2.6-flash

Strongest in Programmatic Reasoning (#27 of 177) and Mathematical Reasoning (#36 of 176); weakest in Reliability (#101 of 177). Abstract Reasoning is estimated, because no results are published yet.

Composite IQ ?

121

#45 of 176 ranked models · ahead of 75%

Xiaomi's #2 model, behind mimo-v2.6-pro (125)

Effective cost

$0.69/1M

$0.14 in · $0.28 out

Speed

56tok/s

48s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

6of 7 dims

16 of 39 benchmarks

Compare with gpt-6.1-solAPI pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

MeasuredEstimated95% range

#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10

Abstract ReasoningAbstract

102estimated

#53 / 201

0/5

-24.5

Mathematical ReasoningMath

129measured

#36 / 176

1/5

-18

Academic ReasoningAcademic

126measured

#70 / 203

4/6

-9.5

Programmatic ReasoningCoding

136measured

#27 / 177

3/6

-13.5

Computer UseComputer Use

120measured

#52 / 176

2/5

-23

ReliabilityReliability

111measured

#101 / 177

2/6

-23

Knowledge WorkKnowledge Work

124measured

#37 / 176

4/6

-7.5

mimo-v2.6-flash95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

16 of 39 Composite IQ benchmarks have a published result for mimo-v2.6-flash. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 102 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 102 shown is estimated from mimo-v2.6-flash's other dimensions and will be replaced as results come in. How estimates work

ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles

Mathematical Reasoning IQ 129 · measuredBest: #21 of 48 on ProofBench 1.11/5

BenchmarkScorePercentileRankLeader · source

ProofBench 1.1

Full source leaderboard reconciliation v1.1 · Oct 27

63.0%

#21 / 48

Leader fable-5.1 · 100%
Full source leaderboard reconciliation v1.1 · Oct 27

Not yet reported

FrontierMath Tier 4FrontierMath Tier 1-3MathArenaAIME

Academic Reasoning IQ 126 · measuredBest: #51 of 159 on CritPt4/6

BenchmarkScorePercentileRankLeader · source

CritPt

Artificial Analysis v4.3.2 · Oct 27

12.0%

#51 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27

SciCode

Artificial Analysis v4.3.2 · Oct 27

51.3%

#57 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

35.1%

#67 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 27

73.1%

#66 / 89

Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

GPQA DiamondMMLU-Pro

Programmatic Reasoning IQ 136 · measuredBest: #16 of 61 on ProgramBench3/6

BenchmarkScorePercentileRankLeader · source

ProgramBench

Full source leaderboard reconciliation · Oct 23

17.5%

#16 / 61

Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 27

22.7%

#29 / 104

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27

IOI V2

Full source leaderboard reconciliation v2 · Oct 27

47.7%

#27 / 43

Leader Gemini 4 Argon · 100%
Full source leaderboard reconciliation v2 · Oct 27

Not yet reported

LiveCodeBenchSWE-rebenchMirrorCode

Computer Use IQ 120 · measuredBest: #7 of 24 on OSWorld-Verified2/5

BenchmarkScorePercentileRankLeader · source

OSWorld-Verified

Full source leaderboard reconciliation · Oct 23

80.8%

#7 / 24

Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23

Arena.ai Agent Arena

Arena.ai Agent Arena · Oct 26

1.0

#35 / 70

Leader opus-5.5 · 20.9
Arena.ai Agent Arena · Oct 26

Not yet reported

BrowseCompMCP AtlasAgents' Last Exam

Reliability IQ 111 · measuredBest: #92 of 154 on AA Long Context Reasoning v1.12/6

BenchmarkScorePercentileRankLeader · source

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

74.3%

#92 / 154

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-12.7

#98 / 158

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding

Knowledge Work IQ 124 · measuredBest: #14 of 106 on AutomationBench-AA4/6

BenchmarkScorePercentileRankLeader · source

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 27

64.1%

#14 / 106

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 27

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 23

55.4%

#20 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 27

1,486

#21 / 111

Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27

GDP.pdf

Artificial Analysis v4.3.2 · Oct 27

9.0%

#65 / 106

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released: Sep 22, 2026
Developer: Xiaomi
Access: Available through Xiaomi MiMo pay-as-you-go API as mimo-v2.6-flash; MIT-licensed RL weights are downloadable from XiaomiMiMo on Hugging Face.
Weights: Open weightsDownloadable and self-hostable
Inputs: textimagevideoaudio
Context: 1,000,000 tokens
API price: $0.14 in · $0.28 outper 1M tokens · full pricing

What Xiaomi says

Native multimodal reasoning with a 1M-token context window and 128K maximum output.
Supports tools, structured output, caching, and agent workflows.
Lower-cost Flash offering for high-frequency professional workflows.

Publisher statements, not AI IQ measurements.

Sourcesmimo.mi.com/docs/en-US/updates/model mimo.mi.com/models/en-US/mimo-v2.6-flashhuggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL

About this score

How much of mimo-v2.6-flash's IQ is measured, and how the rest is estimated.

16/ 39benchmark results

6/ 7dimensions measured

1estimated

0/5Abstract

1/5Math

4/6Academic

3/6Coding

2/5Computer Use

2/6Reliability

4/6Knowledge Work

Bar height = share of benchmarks with resultsEstimatedNo score

Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning has no published results yet, so its IQ is estimated from mimo-v2.6-flash's other dimensions. Missing benchmarks can also draw on its predecessor, Mimo V2 Flash; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare mimo-v2.6-flash

Side-by-side pages for the models it is most often weighed against.

#1 overall

gpt-6.1-sol

IQ141 20 higherEffective cost$6.30 9.1× pricier

Predecessor

mimo-v2-flash

IQ103 18 lowerEffective cost$0.311 2.2× cheaper

Xiaomi #1

mimo-v2.6-pro

IQ125 4 higherEffective cost$1.52 2.2× pricier

Closest IQ

deepseek-v4-flash-vision-exp

IQ121 same IQEffective cost$2.94 4.3× pricier

Most similar profile

haiku-5.5

IQ122 1 higherEffective cost$1.35 2.0× pricier

Similar price

gpt-6-luna

IQ125 4 higherEffective cost$0.768 1.1× pricier

mimo-v2.6-flashComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about mimo-v2.6-flash, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →

What is the IQ of mimo-v2.6-flash?: mimo-v2.6-flash has an estimated IQ of 121, which ranks #45 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is mimo-v2.6-flash best at?: Among the dimensions with published benchmark results, mimo-v2.6-flash ranks highest in Programmatic Reasoning (IQ 136, #27 of 177) and Mathematical Reasoning (IQ 129, #36 of 176). Its lowest-ranked measured dimension is Reliability (IQ 111, #101 of 177).
What is the EQ of mimo-v2.6-flash?: mimo-v2.6-flash doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for mimo-v2.6-flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has mimo-v2.6-flash been tested on?: mimo-v2.6-flash has published results on 16 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, GDPval-AA v2.1 normalized score, AA-Briefcase v1.1 Elo, ProgramBench and Terminal-Bench 4.0.
How much does mimo-v2.6-flash cost?: mimo-v2.6-flash costs $0.14 per million input tokens and $0.28 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.6897 per million input-plus-output tokens.
Is mimo-v2.6-flash open source?: Yes — mimo-v2.6-flash is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed mimo-v2.6-flash?: mimo-v2.6-flash was developed by Xiaomi, based in China.
When was mimo-v2.6-flash released?: mimo-v2.6-flash was publicly released on September 22, 2026.
How large is the context window of mimo-v2.6-flash?: mimo-v2.6-flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is mimo-v2.6-flash?: In independent measurements, mimo-v2.6-flash generates about 56 tokens per second, with a typical response time of about 48 seconds.