Ant GroupReleased Sep 30, 2026
Open weights

Ling 3.1 Flash

Strongest in Programmatic Reasoning (#22 of 181) and Academic Reasoning (#29 of 211); weakest in Reliability (#57 of 181). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?
120
#51 of 180 ranked models · ahead of 72%
China (Other)'s top-ranked model
Effective cost
Not priced
No standard API rate
Speed
214tok/s
13s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
4of 7 dims
10 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract102#58 · est.● Math110#96 · est.● Academic131#29● Coding140#22● Computer Use113#83 · est.● Reliability118#57● Knowledge Work124#41
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
102estimated
#58 / 209
0/5
-30
110estimated
#96 / 180
0/5
-37
131measured
#29 / 211
3/6
-4
140measured
#22 / 181
1/6
-10
113estimated
#83 / 180
0/5
-31.5
118measured
#57 / 181
2/6
-16.5
124measured
#41 / 180
4/6
-8
Ling 3.1 Flash95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

10 of 39 Composite IQ benchmarks have a published result for Ling 3.1 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 Ling 3.1 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 110 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 110 shown is estimated from Ling 3.1 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: #33 of 159 on CritPt3/6
BenchmarkScorePercentileRankLeader · source
CritPt
Artificial Analysis v4.3.2 · Oct 27
18.0%
#33 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
54.1%
#41 / 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
39.4%
#52 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
GPQA DiamondMMLU-ProMMMU-Pro
Programmatic Reasoning IQ 140 · measuredBest: #23 of 109 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v5.0.1 · Nov 13
33.3%
#23 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 113 · estimatedNo published results0/5
No published results yet for Computer Use. The 113 shown is estimated from Ling 3.1 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 118 · measuredBest: #20 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
83.0%
#20 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
2.2
#60 / 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: #18 of 124 on GDPval-AA v2.1 normalized score4/6
BenchmarkScorePercentileRankLeader · source
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 23
55.8%
#18 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23
AutomationBench-AA
Artificial Analysis v5.0.1 · Nov 13
61.7%
#19 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13
AA-Briefcase v1.1 Elo
Artificial Analysis v5.0.1 · Nov 13
1,397
#35 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13
GDP.pdf
Artificial Analysis v5.0.1 · Nov 13
10.0%
#66 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released
Developer
Ant Group
Access
MIT open weights and hosted Ling API access; official open-weight announcement dated October 15, 2026.
Weights
Open weightsDownloadable and self-hostable
Inputs
text
Context
1,000,000 tokens
API price
No per-token rateCurrent standard hosted token pricing for this exact checkpoint remains unverified.

What Ant Group says

  • Publisher announced Ling 3.1 Flash on September 30, 2026.
  • Hybrid reasoning mixture-of-experts model with 560B total and 25B active parameters, with a 1M-token context window.

Limitations

  • The model is text-only.
  • Publisher benchmark claims are distinct from independently mapped results.

Publisher statements, not AI IQ measurements.

About this score

How much of Ling 3.1 Flash's IQ is measured, and how the rest is estimated.

10/ 39benchmark results
4/ 7dimensions measured
3estimated
0/5Abstract
0/5Math
3/6Academic
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 Ling 3.1 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 Ling 3.1 Flash

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

Ling 3.1 FlashComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about Ling 3.1 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 Ling 3.1 Flash?
Ling 3.1 Flash has an estimated IQ of 120, which ranks #51 out of 180 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 Ling 3.1 Flash best at?
Among the dimensions with published benchmark results, Ling 3.1 Flash ranks highest in Programmatic Reasoning (IQ 140, #22 of 181) and Academic Reasoning (IQ 131, #29 of 211). Its lowest-ranked measured dimension is Reliability (IQ 118, #57 of 181).
What is the EQ of Ling 3.1 Flash?
Ling 3.1 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 Ling 3.1 Flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Ling 3.1 Flash been tested on?
Ling 3.1 Flash has published results on 10 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Long Context Reasoning v1.1, GDPval-AA v2.1 normalized score, AutomationBench-AA, CritPt and Terminal-Bench 4.0.
How much does Ling 3.1 Flash cost?
AI IQ doesn't have a verified standard per-token API price for Ling 3.1 Flash, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
Is Ling 3.1 Flash open source?
Yes — Ling 3.1 Flash is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed Ling 3.1 Flash?
Ling 3.1 Flash was developed by Ant Group, based in China.
When was Ling 3.1 Flash released?
Ling 3.1 Flash was publicly released on September 30, 2026.
How large is the context window of Ling 3.1 Flash?
Ling 3.1 Flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is Ling 3.1 Flash?
In independent measurements, Ling 3.1 Flash generates about 214 tokens per second, with a typical response time of about 13 seconds.