Ant GroupReleased Jul 24, 2026
Open weights

Ling 3.0 Flash

Its best results are in Computer Use (#70 of 186) and Knowledge Work (#102 of 186); weakest in Programmatic Reasoning (#139 of 187). Abstract Reasoning and Mathematical Reasoning are estimated, because no results are published yet.

Composite IQ ?
104
#113 of 186 ranked models · ahead of 39%
China (Other)'s #7 model, behind Ling 3.1 Flash (120)
Effective cost
$0.33/1M
$0.07 in · $0.22 out
Speed
245tok/s
13s typical response
Context
262Ktokens
262,144 tokens in
Evidence
5of 7 dims
12 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract85#152 · est.● Math94#152 · est.● Academic117#125● Coding99#139● Computer Use116#70● Reliability111#109● Knowledge Work108#102
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
85estimated
#152 / 221
0/5
-47.5
94estimated
#152 / 186
0/5
-55.5
117measured
#125 / 223
4/6
-18
99measured
#139 / 187
1/6
-52
116measured
#70 / 186
1/5
-30.5
111measured
#109 / 188
2/6
-24.5
108measured
#102 / 186
4/6
-24
Ling 3.0 Flash95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

12 of 39 Composite IQ benchmarks have a published result for Ling 3.0 Flash. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 85 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 85 shown is estimated from Ling 3.0 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 94 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 94 shown is estimated from Ling 3.0 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 117 · measuredBest: #80 of 147 on GPQA Diamond4/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
85.5%
#80 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
23.7%
#105 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
42.0%
#110 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
1.7%
#106 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-ProMMMU-Pro
Programmatic Reasoning IQ 99 · measuredBest: #89 of 109 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 27
0.0%
#89 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 116 · measuredBest: #31 of 45 on BrowseComp1/5
BenchmarkScorePercentileRankLeader · source
BrowseComp
Full source leaderboard reconciliation · Oct 23
72.2%
#31 / 45
Leader Kimi K3.1 Pro · 92.1%
Full source leaderboard reconciliation · Oct 23
Not yet reported
OSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 111 · measuredBest: #98 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
73.0%
#98 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
-17.9
#109 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding
Knowledge Work IQ 108 · measuredBest: #79 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
22.4%
#79 / 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
798
#76 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 27
GDP.pdf
Artificial Analysis v4.3.2 · Oct 27
5.4%
#83 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 27
3.2%
#88 / 112
Leader Gemini 4 Carbon · 77.8%
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
Developer
Ant Group
Access
Open weights and hosted API access through Ant Ling
Weights
Open weightsDownloadable and self-hostable
Inputs
text
Context
262,144 tokens
API price
$0.07 in · $0.22 outper 1M tokens · full pricing

What Ant Group says

  • Ling 3.0 Flash is a 124B-parameter mixture-of-experts model with 5.1B active parameters.
  • It supports hybrid reasoning, tool calling, and a native 256k-token context window.

Limitations

  • The model is text-only.

Publisher statements, not AI IQ measurements.

About this score

How much of Ling 3.0 Flash's IQ is measured, and how the rest is estimated.

12/ 39benchmark results
5/ 7dimensions measured
2estimated
0/5Abstract
0/5Math
4/6Academic
1/6Coding
1/5Computer 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 and Mathematical Reasoning have no published results yet, so their IQ is estimated from Ling 3.0 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 3.0 Flash

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

Ling 3.0 FlashComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about Ling 3.0 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 3.0 Flash?
Ling 3.0 Flash has an estimated IQ of 104, which ranks #113 out of 186 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 3.0 Flash best at?
Among the dimensions with published benchmark results, Ling 3.0 Flash ranks highest in Computer Use (IQ 116, #70 of 186) and Knowledge Work (IQ 108, #102 of 186). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 99, #139 of 187).
What is the EQ of Ling 3.0 Flash?
Ling 3.0 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 3.0 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 3.0 Flash been tested on?
Ling 3.0 Flash has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including GPQA Diamond, Humanity's Last Exam, AA Long Context Reasoning v1.1, GDPval-AA v2.1 normalized score and AA-Briefcase v1.1 Elo.
How much does Ling 3.0 Flash cost?
Ling 3.0 Flash costs $0.075 per million input tokens and $0.22 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.3302 per million input-plus-output tokens.
Is Ling 3.0 Flash open source?
Yes — Ling 3.0 Flash is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed Ling 3.0 Flash?
Ling 3.0 Flash was developed by Ant Group, based in China.
When was Ling 3.0 Flash released?
Ling 3.0 Flash was publicly released on July 24, 2026.
How large is the context window of Ling 3.0 Flash?
Ling 3.0 Flash supports a context window of 262,144 tokens — the amount of text it can consider in a single request.
How fast is Ling 3.0 Flash?
In independent measurements, Ling 3.0 Flash generates about 245 tokens per second, with a typical response time of about 13 seconds.