GoogleReleased Jul 21, 2026
Proprietary

gemini-3.6-flash

Strongest in Academic Reasoning (#41 of 223) and Reliability (#37 of 188); weakest in Programmatic Reasoning (#66 of 187). All seven dimensions are measured.

Composite IQ ?
121
#48 of 186 ranked models · ahead of 75%
Google's #7 model, behind Gemini 4 Carbon (142)
Effective cost
Not priced
No standard API rate
Speed
200tok/s
20s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
7of 7 dims
26 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract106#47● Math123#59● Academic130#41● Coding121#66● Computer Use120#58● Reliability123#37● Knowledge Work122#56
Measured95% 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
106measured
#47 / 221
4/5
-26.5
123measured
#59 / 186
3/5
-26.5
130measured
#41 / 223
5/6
-5
121measured
#66 / 187
3/6
-30
120measured
#58 / 186
2/5
-26.5
123measured
#37 / 188
5/6
-12.5
122measured
#56 / 186
4/6
-10
gemini-3.6-flash95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

26 of 39 Composite IQ benchmarks have a published result for gemini-3.6-flash. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 106 · measuredBest: #14 of 76 on Chess Puzzles4/5
BenchmarkScorePercentileRankLeader · source
Chess Puzzles
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
43.0%
#14 / 76
Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
ARC-AGI-1
Full source leaderboard reconciliation · Oct 23
91.2%
#29 / 73
Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Oct 23
Mystery Game Puzzles
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
30.0%
#26 / 55
Leader gpt-6-astra · 84.0%
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
ARC-AGI-2
Full source leaderboard reconciliation · Oct 23
60.4%
#36 / 73
Leader gpt-6.2-astra · 95.8%
Full source leaderboard reconciliation · Oct 23
Not yet reported
ARC-AGI-3
Mathematical Reasoning IQ 123 · measuredBest: #44 of 89 on FrontierMath Tier 1-33/5
BenchmarkScorePercentileRankLeader · source
FrontierMath Tier 1-3
Full source leaderboard reconciliation · Oct 23
58.9%
#44 / 89
Leader fable-5.2 · 95.1%
Full source leaderboard reconciliation · Oct 23
MathArena
Full source leaderboard reconciliation · Nov 18
21.3%
#42 / 70
Leader gpt-6.2-astra · 92.2%
Full source leaderboard reconciliation · Nov 18
FrontierMath Tier 4
Full source leaderboard reconciliation · Oct 23
22.0%
#48 / 77
Leader fable-5.2 · 100%
Full source leaderboard reconciliation · Oct 23
Not yet reported
ProofBench 1.1AIME
Academic Reasoning IQ 130 · measuredBest: #20 of 147 on GPQA Diamond5/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
92.8%
#20 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
MMMU-Pro
Artificial Analysis v4.3.2 · Oct 27
83.2%
#14 / 90
Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
53.4%
#44 / 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
40.8%
#45 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
10.6%
#59 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 121 · measuredBest: #49 of 109 on Terminal-Bench 4.03/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 27
7.1%
#49 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27
ProgramBench
Full source leaderboard reconciliation · Oct 23
2.5%
#41 / 63
Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23
IOI V2
Full source leaderboard reconciliation v2 · Oct 27
35.1%
#37 / 43
Leader Gemini 4 Argon · 100%
Full source leaderboard reconciliation v2 · Oct 27
Not yet reported
LiveCodeBenchSWE-rebenchMirrorCode
Computer Use IQ 120 · measuredBest: #4 of 24 on OSWorld-Verified2/5
BenchmarkScorePercentileRankLeader · source
OSWorld-Verified
Full source leaderboard reconciliation · Oct 23
83.0%
#4 / 24
Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23
Arena.ai Agent Arena
Arena.ai Agent Arena · Oct 13
-4.4
#56 / 77
Leader fable-5.2 · 27.4
Arena.ai Agent Arena · Oct 13
Not yet reported
BrowseCompMCP AtlasAgents' Last Exam
Reliability IQ 123 · measuredBest: #26 of 158 on AA Omniscience5/6
BenchmarkScorePercentileRankLeader · source
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
22.1
#26 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
SimpleQA Verified
Full source leaderboard reconciliation · Oct 23
66.2%
#19 / 85
Leader fable-5.2 · 94.0%
Full source leaderboard reconciliation · Oct 23
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
80.0%
#45 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
FACTS Grounding
Full source leaderboard reconciliation · Nov 13
66.6%
#23 / 47
Leader gpt-6.1-terra · 84.2%
Full source leaderboard reconciliation · Nov 13
BullshitBench v2
Full source leaderboard reconciliation · Oct 23
28.0%
#68 / 96
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23
Not yet reported
IFBench
Knowledge Work IQ 122 · measuredBest: #37 of 111 on GDP.pdf4/6
BenchmarkScorePercentileRankLeader · source
GDP.pdf
Artificial Analysis v4.3.2 · Oct 27
17.4%
#37 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 27
53.0%
#40 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v4.3.2 · Oct 27
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 20
39.2%
#49 / 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
955
#60 / 116
Leader sonnet-5.5 · 1,816
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
Google
Access
Generally available through the Gemini API and Google AI Studio
Weights
ProprietaryHosted access only
Inputs
textimagevideoaudio
Context
1,000,000 tokens

What Google says

  • Google emphasizes improved token efficiency, planning, and agentic performance.
  • The model supports a 1M-token context window and configurable reasoning.

Publisher statements, not AI IQ measurements.

About this score

How much of gemini-3.6-flash's IQ is measured, and how the rest is estimated.

26/ 39benchmark results
7/ 7dimensions measured
0estimated
4/5Abstract
3/5Math
5/6Academic
3/6Coding
2/5Computer Use
5/6Reliability
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.

How gaps are handled

Every dimension has at least one published result. Missing benchmarks can also draw on its predecessors, Gemini 3.5 Flash and Gemini 3 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 gemini-3.6-flash

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

gemini-3.6-flashComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about gemini-3.6-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 gemini-3.6-flash?
gemini-3.6-flash has an estimated IQ of 121, which ranks #48 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 gemini-3.6-flash best at?
Among the dimensions with published benchmark results, gemini-3.6-flash ranks highest in Academic Reasoning (IQ 130, #41 of 223) and Reliability (IQ 123, #37 of 188). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 121, #66 of 187).
What is the EQ of gemini-3.6-flash?
gemini-3.6-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 gemini-3.6-flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gemini-3.6-flash been tested on?
gemini-3.6-flash has published results on 26 of the 39 benchmarks behind AI IQ's Composite IQ, including GPQA Diamond, MMMU-Pro, AA Omniscience, OSWorld-Verified and Chess Puzzles.
How much does gemini-3.6-flash cost?
AI IQ doesn't have a verified standard per-token API price for gemini-3.6-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 gemini-3.6-flash open source?
No — gemini-3.6-flash is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gemini-3.6-flash?
gemini-3.6-flash was developed by Google, based in the United States.
When was gemini-3.6-flash released?
gemini-3.6-flash was publicly released on July 21, 2026.
How large is the context window of gemini-3.6-flash?
gemini-3.6-flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is gemini-3.6-flash?
In independent measurements, gemini-3.6-flash generates about 200 tokens per second, with a typical response time of about 20 seconds.