GoogleReleased Jul 21, 2026
Proprietary

gemini-3.5-flash-lite

Strongest in Reliability (#53 of 188) and Knowledge Work (#79 of 186); weakest in Programmatic Reasoning (#168 of 187). All seven dimensions are measured.

Composite IQ ?
104
#111 of 186 ranked models · ahead of 41%
Google's #13 model, behind Gemini 4 Carbon (142)
Effective cost
$1.31/1M
$0.30 in · $2.50 out
Speed
419tok/s
9s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
7of 7 dims
24 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract86#141● Math95#147● Academic114#132● Coding93#168● Computer Use107#109● Reliability119#53● Knowledge Work113#79
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
86measured
#141 / 221
4/5
-46.5
95measured
#147 / 186
2/5
-54.5
114measured
#132 / 223
5/6
-21
93measured
#168 / 187
2/6
-58
107measured
#109 / 186
2/5
-39.5
119measured
#53 / 188
4/6
-16.5
113measured
#79 / 186
5/6
-19
gemini-3.5-flash-lite95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

24 of 39 Composite IQ benchmarks have a published result for gemini-3.5-flash-lite. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 86 · measuredBest: #46 of 76 on Chess Puzzles4/5
BenchmarkScorePercentileRankLeader · source
Chess Puzzles
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
22.0%
#46 / 76
Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
Mystery Game Puzzles
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
19.0%
#41 / 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
10.3%
#55 / 73
Leader gpt-6.2-astra · 95.8%
Full source leaderboard reconciliation · Oct 23
ARC-AGI-1
Full source leaderboard reconciliation · Oct 23
53.5%
#59 / 73
Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Oct 23
Not yet reported
ARC-AGI-3
Mathematical Reasoning IQ 95 · measuredBest: #73 of 89 on FrontierMath Tier 1-32/5
BenchmarkScorePercentileRankLeader · source
FrontierMath Tier 1-3
Full source leaderboard reconciliation · Oct 23
26.0%
#73 / 89
Leader fable-5.2 · 95.1%
Full source leaderboard reconciliation · Oct 23
FrontierMath Tier 4
Full source leaderboard reconciliation · Oct 23
0.0%
#75 / 77
Leader fable-5.2 · 100%
Full source leaderboard reconciliation · Oct 23
Not yet reported
ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 114 · measuredBest: #33 of 90 on MMMU-Pro5/6
BenchmarkScorePercentileRankLeader · source
MMMU-Pro
Artificial Analysis v5.0.1 · Nov 13
79.0%
#33 / 90
Leader fable-5.1 · 90.6%
Artificial Analysis v5.0.1 · Nov 13
GPQA Diamond
Artificial Analysis v5.0.1 · Nov 13
83.8%
#89 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v5.0.1 · Nov 13
SciCode
Artificial Analysis v4.3.2 · Oct 27
41.3%
#111 / 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
18.8%
#122 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
0.0%
#137 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 93 · measuredBest: #60 of 109 on Terminal-Bench 4.02/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v5.0.1 · Nov 13
1.0%
#60 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v5.0.1 · Nov 13
ProgramBench
Full source leaderboard reconciliation · Oct 23
0.0%
#56 / 63
Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23
Not yet reported
LiveCodeBenchIOI V2SWE-rebenchMirrorCode
Computer Use IQ 107 · measuredBest: #14 of 24 on OSWorld-Verified2/5
BenchmarkScorePercentileRankLeader · source
OSWorld-Verified
Full source leaderboard reconciliation · Oct 23
74.0%
#14 / 24
Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23
-15.3
#72 / 77
Leader fable-5.2 · 27.4
Not yet reported
BrowseCompMCP AtlasAgents' Last Exam
Reliability IQ 119 · measuredBest: #25 of 96 on BullshitBench v24/6
BenchmarkScorePercentileRankLeader · source
BullshitBench v2
Full source leaderboard reconciliation · Oct 23
60.0%
#25 / 96
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
5.2
#53 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
76.0%
#83 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
FACTS Grounding
Full source leaderboard reconciliation · Nov 13
65.9%
#26 / 47
Leader gpt-6.1-terra · 84.2%
Full source leaderboard reconciliation · Nov 13
Not yet reported
SimpleQA VerifiedIFBench
Knowledge Work IQ 113 · measuredBest: #47 of 111 on GDP.pdf5/6
BenchmarkScorePercentileRankLeader · source
GDP.pdf
Artificial Analysis v5.0.1 · Nov 13
13.6%
#47 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13
AutomationBench-AA
Artificial Analysis v5.0.1 · Nov 13
25.0%
#57 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 23
24.1%
#75 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23
EnterpriseOps-Gym-AA
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
42.3%
#20 / 31
Leader fable-5 · 51.1%
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
AA-Briefcase v1.1 Elo
Artificial Analysis v5.0.1 · Nov 13
651
#86 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
AA-AnalystAgent

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
API price
$0.30 in · $2.50 outper 1M tokens · full pricing

What Google says

  • Google positions Flash-Lite for low-latency, high-volume workloads.
  • The model supports a 1M-token context window with multimodal input.

Publisher statements, not AI IQ measurements.

About this score

How much of gemini-3.5-flash-lite's IQ is measured, and how the rest is estimated.

24/ 39benchmark results
7/ 7dimensions measured
0estimated
4/5Abstract
2/5Math
5/6Academic
2/6Coding
2/5Computer Use
4/6Reliability
5/6Knowledge 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 predecessor, Gemini 3.1 Flash Lite; 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-3.5-flash-lite

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

gemini-3.5-flash-liteComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about gemini-3.5-flash-lite, 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-3.5-flash-lite?
gemini-3.5-flash-lite has an estimated IQ of 104, which ranks #111 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-3.5-flash-lite best at?
Among the dimensions with published benchmark results, gemini-3.5-flash-lite ranks highest in Reliability (IQ 119, #53 of 188) and Knowledge Work (IQ 113, #79 of 186). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 93, #168 of 187).
What is the EQ of gemini-3.5-flash-lite?
gemini-3.5-flash-lite 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-3.5-flash-lite. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gemini-3.5-flash-lite been tested on?
gemini-3.5-flash-lite has published results on 24 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, AA Omniscience, MMMU-Pro, GDP.pdf and AutomationBench-AA.
How much does gemini-3.5-flash-lite cost?
gemini-3.5-flash-lite costs $0.30 per million input tokens and $2.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $1.31 per million input-plus-output tokens.
Is gemini-3.5-flash-lite open source?
No — gemini-3.5-flash-lite is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gemini-3.5-flash-lite?
gemini-3.5-flash-lite was developed by Google, based in the United States.
When was gemini-3.5-flash-lite released?
gemini-3.5-flash-lite was publicly released on July 21, 2026.
How large is the context window of gemini-3.5-flash-lite?
gemini-3.5-flash-lite supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is gemini-3.5-flash-lite?
In independent measurements, gemini-3.5-flash-lite generates about 419 tokens per second, with a typical response time of about 8.6 seconds.