XiaomiReleased Apr 26, 2026
Open weights

mimo-v2.5-pro

Strongest in Reliability (#39 of 177) and Mathematical Reasoning (#46 of 176); weakest in Computer Use (#78 of 176). Abstract Reasoning is estimated, because no results are published yet.

Composite IQ ?
114
#63 of 176 ranked models · ahead of 65%
Xiaomi's #3 model, behind mimo-v2.6-pro (125)
Effective cost
$0.647/1M
$0.43 in · $0.87 out
Speed
51tok/s
50s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
6of 7 dims
16 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract87#122 · est.● Math126#46● Academic124#77● Coding115#72● Computer Use113#78● Reliability121#39● Knowledge Work113#76
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
87estimated
#122 / 201
0/5
-39.5
126measured
#46 / 176
1/5
-21
124measured
#77 / 203
4/6
-11.5
115measured
#72 / 177
2/6
-34.5
113measured
#78 / 176
1/5
-30
121measured
#39 / 177
4/6
-13
113measured
#76 / 176
4/6
-18.5
mimo-v2.5-pro95% 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-v2.5-pro. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 87 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 87 shown is estimated from mimo-v2.5-pro'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 126 · measuredBest: #38 of 48 on ProofBench 1.11/5
BenchmarkScorePercentileRankLeader · source
ProofBench 1.1
Full source leaderboard reconciliation v1.1 · Oct 27
22.0%
#38 / 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 124 · measuredBest: #61 of 167 on SciCode4/6
BenchmarkScorePercentileRankLeader · source
SciCode
Artificial Analysis v4.3.2 · Oct 27
50.6%
#61 / 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
35.7%
#65 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
86.6%
#73 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
4.0%
#87 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-ProMMMU-Pro
Programmatic Reasoning IQ 115 · measuredBest: #18 of 25 on SWE-rebench2/6
BenchmarkScorePercentileRankLeader · source
SWE-rebench
Full source leaderboard reconciliation · Oct 23
46.5%
#18 / 25
Leader fable-5 · 64.5%
Full source leaderboard reconciliation · Oct 23
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 27
0.0%
#91 / 104
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
LiveCodeBenchIOI V2ProgramBenchMirrorCode
Computer Use IQ 113 · measuredBest: #61 of 70 on Arena.ai Agent Arena1/5
BenchmarkScorePercentileRankLeader · source
Arena.ai Agent Arena
Arena.ai Agent Arena · Oct 26
-8.9
#61 / 70
Leader opus-5.5 · 20.9
Arena.ai Agent Arena · Oct 26
Not yet reported
BrowseCompOSWorld-VerifiedMCP AtlasAgents' Last Exam
Reliability IQ 121 · measuredBest: #6 of 96 on IFBench4/6
BenchmarkScorePercentileRankLeader · source
IFBench
Artificial Analysis v4.3.2 · Oct 27
79.9%
#6 / 96
Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27
BullshitBench v2
Full source leaderboard reconciliation · Oct 23
62.0%
#17 / 83
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
79.7%
#52 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
3.3
#59 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedFACTS Grounding
Knowledge Work IQ 113 · measuredBest: #58 of 124 on GDPval-AA v2.1 normalized score4/6
BenchmarkScorePercentileRankLeader · source
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 20
31.0%
#58 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20
AA-Briefcase v1.1 Elo
Artificial Analysis v4.3.2 · Oct 27
883
#62 / 111
Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 27
13.7%
#65 / 106
Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 27
GDP.pdf
Artificial Analysis v4.3.2 · Oct 27
4.0%
#86 / 106
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released
Developer
Xiaomi
Weights
Open weightsDownloadable and self-hostable
Context
1,000,000 tokens
API price
$0.43 in · $0.87 outper 1M tokens · full pricing

About this score

How much of mimo-v2.5-pro's IQ is measured, and how the rest is estimated.

16/ 39benchmark results
6/ 7dimensions measured
1estimated
0/5Abstract
1/5Math
4/6Academic
2/6Coding
1/5Computer Use
4/6Reliability
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-v2.5-pro's other dimensions. Missing benchmarks can also draw on its predecessor, Mimo V2 Pro; 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-v2.5-pro

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

mimo-v2.5-proComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about mimo-v2.5-pro, 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-v2.5-pro?
mimo-v2.5-pro has an estimated IQ of 114, which ranks #63 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-v2.5-pro best at?
Among the dimensions with published benchmark results, mimo-v2.5-pro ranks highest in Reliability (IQ 121, #39 of 177) and Mathematical Reasoning (IQ 126, #46 of 176). Its lowest-ranked measured dimension is Computer Use (IQ 113, #78 of 176).
What is the EQ of mimo-v2.5-pro?
mimo-v2.5-pro has an estimated EQ of 113. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
Which benchmarks has mimo-v2.5-pro been tested on?
mimo-v2.5-pro has published results on 16 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, BullshitBench v2, AA Long Context Reasoning v1.1, SciCode and AA Omniscience.
How much does mimo-v2.5-pro cost?
mimo-v2.5-pro costs $0.435 per million input tokens and $0.87 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.6471 per million input-plus-output tokens.
Is mimo-v2.5-pro open source?
Yes — mimo-v2.5-pro is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed mimo-v2.5-pro?
mimo-v2.5-pro was developed by Xiaomi, based in China.
When was mimo-v2.5-pro released?
mimo-v2.5-pro was publicly released on April 26, 2026.
How large is the context window of mimo-v2.5-pro?
mimo-v2.5-pro supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is mimo-v2.5-pro?
In independent measurements, mimo-v2.5-pro generates about 51 tokens per second, with a typical response time of about 50 seconds.