What is the IQ of MiniMax M3.1 Flash?

MiniMax M3.1 Flash has an estimated IQ of 123, which ranks #32 out of 173 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 MiniMax M3.1 Flash best at?

Among the dimensions with published benchmark results, MiniMax M3.1 Flash ranks highest in Academic Reasoning (IQ 131, #19 of 199) and Knowledge Work (IQ 128, #17 of 173). Its lowest-ranked measured dimension is Reliability (IQ 121, #33 of 173).

What is the EQ of MiniMax M3.1 Flash?

MiniMax M3.1 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 MiniMax M3.1 Flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has MiniMax M3.1 Flash been tested on?

MiniMax M3.1 Flash has published results on 11 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, Humanity's Last Exam, CritPt, AA Omniscience and AA-Briefcase v1.1 Elo.

How much does MiniMax M3.1 Flash cost?

MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $1.40 per million input-plus-output tokens.

Is MiniMax M3.1 Flash open source?

No — MiniMax M3.1 Flash is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed MiniMax M3.1 Flash?

MiniMax M3.1 Flash was developed by MiniMax, based in China.

When was MiniMax M3.1 Flash released?

MiniMax M3.1 Flash was publicly released on October 19, 2026.

How large is the context window of MiniMax M3.1 Flash?

MiniMax M3.1 Flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is MiniMax M3.1 Flash?

In independent measurements, MiniMax M3.1 Flash generates about 96 tokens per second, with a typical response time of about 28 seconds.

MiniMaxReleased Oct 19, 2026

NewProprietary

MiniMax M3.1 Flash

Strongest in Academic Reasoning (#19 of 199) and Knowledge Work (#17 of 173); weakest in Reliability (#33 of 173). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?

123

#32 of 173 ranked models · ahead of 82%

MiniMax's top-ranked model

Effective cost

$1.40/1M

$0.15 in · $0.60 out

Speed

96tok/s

28s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

4of 7 dims

11 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

#46 / 197

0/5

-25.5

Mathematical ReasoningMath

120estimated

#61 / 173

0/5

-26

Academic ReasoningAcademic

131measured

#19 / 199

4/6

-4

Programmatic ReasoningCoding

136measured

#25 / 174

1/6

-12.5

Computer UseComputer Use

121estimated

#49 / 173

0/5

-21

ReliabilityReliability

121measured

#33 / 173

2/6

-11.5

Knowledge WorkKnowledge Work

128measured

#17 / 173

4/6

-3

MiniMax M3.1 Flash95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

11 of 39 Composite IQ benchmarks have a published result for MiniMax M3.1 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 MiniMax M3.1 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 120 · estimatedNo published results0/5

No published results yet for Mathematical Reasoning. The 120 shown is estimated from MiniMax M3.1 Flash's other dimensions and will be replaced as results come in. How estimates work

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME

Academic Reasoning IQ 131 · measuredBest: #16 of 165 on Humanity's Last Exam4/6

BenchmarkScorePercentileRankLeader · source

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 23

48.0%

#16 / 165

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 23

CritPt

Artificial Analysis v4.3.2 · Oct 23

22.3%

#20 / 157

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 23

SciCode

Artificial Analysis v4.3.2 · Oct 23

53.4%

#43 / 165

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 23

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 23

79.1%

#30 / 87

Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 23

Not yet reported

GPQA DiamondMMLU-Pro

Programmatic Reasoning IQ 136 · measuredBest: #25 of 102 on Terminal-Bench 4.01/6

BenchmarkScorePercentileRankLeader · source

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 23

25.8%

#25 / 102

Leader sonnet-5.5 · 63.6%
Artificial Analysis v4.3.2 · Oct 23

Not yet reported

LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 121 · estimatedNo published results0/5

No published results yet for Computer Use. The 121 shown is estimated from MiniMax M3.1 Flash's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 121 · measuredBest: #31 of 156 on AA Omniscience2/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 23

15.6

#31 / 156

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 23

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 23

79.7%

#51 / 152

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 23

Not yet reported

SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding

Knowledge Work IQ 128 · measuredBest: #2 of 104 on AutomationBench-AA4/6

BenchmarkScorePercentileRankLeader · source

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 23

72.5%

#2 / 104

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 23

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 23

1,474

#24 / 109

Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 23

GDP.pdf

Artificial Analysis v4.3.2 · Oct 23

20.8%

#23 / 104

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 23

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 23

47.9%

#33 / 124

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

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released: Oct 19, 2026
Developer: MiniMax
Access: Available through the MiniMax API, M Plan and MiniMax Code.
Weights: ProprietaryHosted access only
Inputs: textimage
Context: 1,000,000 tokens
API price: $0.15 in · $0.60 outper 1M tokens · full pricing

What MiniMax says

MiniMax announced M3.1 Flash on October 19, 2026.
Multimodal coding model with a 1M-token context window and tunable thinking depth.
Standard API prices are $0.15 input, $0.60 output and $0.015 cached input per million tokens.

Limitations

Model weights were not yet released when checked on October 20.
The earlier Space Bunny and Flash Preview configurations are not assumed to be the final released checkpoint.

Publisher statements, not AI IQ measurements.

Sourcesminimax.io/blog/minimax-m31f platform.minimax.io/docs/guides/models-intro

About this score

How much of MiniMax M3.1 Flash's IQ is measured, and how the rest is estimated.

11/ 39benchmark results

4/ 7dimensions measured

3estimated

0/5Abstract

0/5Math

4/6Academic

1/6Coding

0/5Computer 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, Mathematical Reasoning and Computer Use have no published results yet, so their IQ is estimated from MiniMax M3.1 Flash's other dimensions.

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 MiniMax M3.1 Flash

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

#1 overall

gpt-6.1-sol

IQ141 18 higherEffective cost$6.25 4.5× pricier

Closest IQ

Qwen3.8 2.4T A95B

IQ123 same IQEffective cost$12.99 9.3× pricier

Most similar profile

Qwen3.8 Max

IQ123 same IQEffective cost$11.06 7.9× pricier

Similar price

qwen3.7-plus

IQ112 11 lowerEffective cost$1.42 about the same

#2 overall

opus-5.5

IQ141 18 higherEffective cost$35.41 25.3× pricier

#3 overall

Gemini 4 Argon

IQ140 17 higher

MiniMax M3.1 FlashComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about MiniMax M3.1 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 MiniMax M3.1 Flash?: MiniMax M3.1 Flash has an estimated IQ of 123, which ranks #32 out of 173 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 MiniMax M3.1 Flash best at?: Among the dimensions with published benchmark results, MiniMax M3.1 Flash ranks highest in Academic Reasoning (IQ 131, #19 of 199) and Knowledge Work (IQ 128, #17 of 173). Its lowest-ranked measured dimension is Reliability (IQ 121, #33 of 173).
What is the EQ of MiniMax M3.1 Flash?: MiniMax M3.1 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 MiniMax M3.1 Flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has MiniMax M3.1 Flash been tested on?: MiniMax M3.1 Flash has published results on 11 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, Humanity's Last Exam, CritPt, AA Omniscience and AA-Briefcase v1.1 Elo.
How much does MiniMax M3.1 Flash cost?: MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $1.40 per million input-plus-output tokens.
Is MiniMax M3.1 Flash open source?: No — MiniMax M3.1 Flash is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed MiniMax M3.1 Flash?: MiniMax M3.1 Flash was developed by MiniMax, based in China.
When was MiniMax M3.1 Flash released?: MiniMax M3.1 Flash was publicly released on October 19, 2026.
How large is the context window of MiniMax M3.1 Flash?: MiniMax M3.1 Flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is MiniMax M3.1 Flash?: In independent measurements, MiniMax M3.1 Flash generates about 96 tokens per second, with a typical response time of about 28 seconds.