Gemini 3.5 Flash vs Gemini 3 Flash Preview

Gemini 3 Flash Preview leads Gemini 3.5 Flash on coding, 43.7 to 39.8 on the Vibe Coding Index, and Gemini 3 Flash Preview costs 3.0x less per output token ($3.00 vs $9.00 per million). Updated October 22, 2026; 57 benchmarks have a result for both.

Replace Gemini 3.5 Flash Replace Gemini 3 Flash Preview

Gemini 3.5 FlashGoogle

Coding: 39.8
Overall: 63.8
Output $/M: $9.00

Gemini 3 Flash PreviewGoogle

Coding: 43.7
Overall: 55.0
Output $/M: $3.00

vs boards won of 57 shared, 2 tied

Gemini 3.5 Flash or Gemini 3 Flash Preview: which to pick

Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash, though on 2 benchmarks against 4.

Pick Gemini 3.5 Flash for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Model AGemini 3.5 FlashGoogle39.8/1004 independent benchmarks$1.21 per solved task Model BGemini 3 Flash PreviewGoogle43.7/1002 independent benchmarks$0.37 per solved task

575815

Shared results: 57
Gemini 3.5 Flash only: 58
Gemini 3 Flash Preview only: 15
Like-for-like categories: 8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

Coding
Vibe Coding Index, six public coding benchmarks
Gemini 3 Flash Preview
Gemini 3 Flash Preview scores 43.7 against 39.8.
4 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 33.6 against 26.3.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 92.7% against 87.9%.
Same board, both measured
Math
AIME
No call
Only Gemini 3 Flash Preview has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 89.5% against 88.6%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 1267 against 1196.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Gemini 3.5 Flash $0.0060, Gemini 3 Flash Preview $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Gemini 3.5 Flash $1.21, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.5 Flash 39.8 from 4 benchmarks, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
Widest category: Agentic work, 15.4 points apart on average over 13 shared benchmarks.
Widest single gap: ARC-AGI-2: Gemini 3.5 Flash 72.1% against Gemini 3 Flash Preview 33.6%, 38.5 points apart on a 0 to 100 scale.
Output price: Gemini 3.5 Flash $9.00 against Gemini 3 Flash Preview $3.00 per million output tokens, 3.0x apart.
Context window: Both take 1.05M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Category	Gemini 3.5 Flash	Gemini 3 Flash Preview	Ties
Coding	7	2	1 tie
Intelligence	1	0
Agentic work	12	1
Reasoning	10	0
Math	3	0	1 tie
Knowledge	2	6
Web design	4	0
General	4	3
All shared boards	43	12	2 ties

CodingLike-for-likeSix of these boards feed the Vibe Coding Index72

Coding benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
SWE-bench Verified	Not measured	75.8%	Only Gemini 3 Flash Preview measured
LMArena WebDev	1499	Not measured	Only Gemini 3.5 Flash measured
LiveCodeBench (Vals AI)	87.6%	85.6%	Gemini 3.5 Flash
SWE-bench Verified (Vals AI)	78.8%	75.0%	Gemini 3.5 Flash
Terminal-Bench 4 (Vals AI)	6.1%	Not measured	Only Gemini 3.5 Flash measured
Vibe Code Bench (Vals AI)	48.7%	20.2%	Gemini 3.5 Flash
Code migration (Vals AI)	26.8%	6.4%	Gemini 3.5 Flash
ProgramBench (Vals AI)	0.0%	0.0%	Tie
Terminal-Bench 2.1 (Vals AI)	74.2%	53.9%	Gemini 3.5 Flash
SkillsBench (Vals AI)	52.7%	Not measured	Only Gemini 3.5 Flash measured
LiveCodeBench (Artificial Analysis run)	Not measured	90.8%	Only Gemini 3 Flash Preview measured
SciCode	53.9%	Not measured	Only Gemini 3.5 Flash measured
Terminal-Bench Hard (Artificial Analysis run)	46.2%	38.6%	Gemini 3.5 Flash
Terminal-Bench	Not measured	64.3%	Only Gemini 3 Flash Preview measured
GSO-Bench	Not measured	9.8%	Only Gemini 3 Flash Preview measured
WeirdML	62.6%	61.6%	Gemini 3.5 Flash
ALE-Bench	911.0	1367.2	Gemini 3 Flash Preview
LMArena Text: coding	1493	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: software and IT	1494	Not measured	Only Gemini 3.5 Flash measured
LMArena WebDev: React	1495	Not measured	Only Gemini 3.5 Flash measured
LMArena WebDev: HTML	1522	Not measured	Only Gemini 3.5 Flash measured
LMArena WebDev: from an image	1504	Not measured	Only Gemini 3.5 Flash measured
SciCode	12.3%	12.7%	Gemini 3 Flash Preview
Neither model has a result on the other 20 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10

Intelligence benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
AA Intelligence Index	33.6	26.3	Gemini 3.5 Flash
Epoch Capabilities Index	154.9	Not measured	Only Gemini 3.5 Flash measured

Agentic workLike-for-likePublic boards, shown as published, kept out of the index121

Agentic work benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
Design Arena: agents building web apps	1202	1111	Gemini 3.5 Flash
Design Arena: agents building full-stack apps	1197	1063	Gemini 3.5 Flash
Design Arena: agents building mobile apps	1175	1090	Gemini 3.5 Flash
Design Arena: agents building Android apps	1184	1051	Gemini 3.5 Flash
Design Arena: agents building Godot games	1098	1161	Gemini 3 Flash Preview
Design Arena: agents building games	1180	Not measured	Only Gemini 3.5 Flash measured
Design Arena: HTML slides	1082	Not measured	Only Gemini 3.5 Flash measured
Design Arena: PowerPoint slides	1153	1036	Gemini 3.5 Flash
Finance Agent (Vals AI)	57.9%	42.5%	Gemini 3.5 Flash
Tax Agent Bench (Vals AI)	21.6%	11.8%	Gemini 3.5 Flash
Legal Research Bench (Vals AI)	30.8%	18.3%	Gemini 3.5 Flash
Excel Modeling Benchmark (Vals AI)	63.5%	26.0%	Gemini 3.5 Flash
Terminal-Bench-Science (Vals AI)	5.7%	Not measured	Only Gemini 3.5 Flash measured
τ²-Bench Telecom	95.6%	80.4%	Gemini 3.5 Flash
APEX-Agents	27.5%	Not measured	Only Gemini 3.5 Flash measured
BALROG	Not measured	48.1%	Only Gemini 3 Flash Preview measured
DeepResearch Bench	Not measured	49.8%	Only Gemini 3 Flash Preview measured
Vending-Bench 2	$5,396	$3,635	Gemini 3.5 Flash
MCP Atlas	83.6%	62.0%	Gemini 3.5 Flash
Neither model has a result on the other 23 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index100

Reasoning benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
GPQA Diamond	92.7%	87.9%	Gemini 3.5 Flash
MMMU Pro (Vals AI)	88.3%	87.6%	Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)	92.2%	89.8%	Gemini 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)	42.7%	36.6%	Gemini 3.5 Flash
GPQA Diamond (Epoch AI run)	92.8%	89.4%	Gemini 3.5 Flash
ARC-AGI	92.5%	84.7%	Gemini 3.5 Flash
ARC-AGI-2	72.1%	33.6%	Gemini 3.5 Flash
SimpleBench	76.7%	61.1%	Gemini 3.5 Flash
Chess puzzles	45.0%	39.0%	Gemini 3.5 Flash
Mystery game puzzles	32.0%	26.0%	Gemini 3.5 Flash
EBR-bench	4.8%	Not measured	Only Gemini 3.5 Flash measured
VPCT	Not measured	72.6%	Only Gemini 3 Flash Preview measured
LMArena Text: hard prompts	1488	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: expert	1495	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: hard prompts in English	1483	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: diagrams	1323	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: homework	1330	Not measured	Only Gemini 3.5 Flash measured
Neither model has a result on the other 6 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index30

Math benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
AIME	Not measured	95.6%	Only Gemini 3 Flash Preview measured
MGSM (Vals AI)	Not measured	93.3%	Only Gemini 3 Flash Preview measured
AA Math Index	Not measured	97.0	Only Gemini 3 Flash Preview measured
AIME 2025 (Artificial Analysis run)	Not measured	97.0%	Only Gemini 3 Flash Preview measured
OTIS Mock AIME	95.6%	95.6%	Tie
FrontierMath, tiers 1 to 3	62.8%	51.2%	Gemini 3.5 Flash
FrontierMath, tier 4	26.8%	17.1%	Gemini 3.5 Flash
ProofBench	31.0%	15.0%	Gemini 3.5 Flash
LMArena Text: math	1504	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: mathematical work	1495	Not measured	Only Gemini 3.5 Flash measured
MathArena	24.7%	Not measured	Only Gemini 3.5 Flash measured
Neither model has a result on the other 3 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index26

Knowledge benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
MMLU Pro	89.5%	88.6%	Gemini 3.5 Flash
LegalBench (Vals AI)	83.6%	86.9%	Gemini 3 Flash Preview
CaseLaw (Vals AI)	Not measured	55.8%	Only Gemini 3 Flash Preview measured
CorpFin (Vals AI)	64.7%	66.4%	Gemini 3 Flash Preview
TaxEval (Vals AI)	74.4%	73.9%	Gemini 3.5 Flash
MortgageTax (Vals AI)	68.1%	68.7%	Gemini 3 Flash Preview
MedQA (Vals AI)	Not measured	95.8%	Only Gemini 3 Flash Preview measured
MedCode (Vals AI)	55.8%	55.9%	Gemini 3 Flash Preview
MMLU Pro (Artificial Analysis run)	Not measured	89.0%	Only Gemini 3 Flash Preview measured
SimpleQA Verified	66.2%	66.8%	Gemini 3 Flash Preview
GeoBench	Not measured	88.0%	Only Gemini 3 Flash Preview measured
LMArena Text: science	1495	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: medicine and healthcare	1483	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: legal and government	1488	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: business and finance	1467	Not measured	Only Gemini 3.5 Flash measured
FACTS Benchmark Suite	63.1%	63.4%	Gemini 3 Flash Preview
Neither model has a result on the other 4 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index40

Web design benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
Design Arena: websites	1267	1196	Gemini 3.5 Flash
Design Arena: UI components	1270	Not measured	Only Gemini 3.5 Flash measured
Design Arena: game dev	1263	1165	Gemini 3.5 Flash
Design Arena: data viz	1237	Not measured	Only Gemini 3.5 Flash measured
Design Arena: 3D	1243	1183	Gemini 3.5 Flash
Design Arena: all code categories	1266	1189	Gemini 3.5 Flash
Design Arena: SVG	1253	Not measured	Only Gemini 3.5 Flash measured
Design Arena: ASCII art	1254	Not measured	Only Gemini 3.5 Flash measured
Neither model has a result on the other 1 board here

GeneralLike-for-likePublic boards, shown as published, kept out of the index43

General benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
Public Benefits Bench (Vals AI)	59.5%	Not measured	Only Gemini 3.5 Flash measured
SAGE (Vals AI)	49.9%	51.8%	Gemini 3 Flash Preview
MedScribe (Vals AI)	76.6%	69.9%	Gemini 3.5 Flash
Vals Multimodal Index	62.9%	52.2%	Gemini 3.5 Flash
IFBench	76.3%	78.0%	Gemini 3 Flash Preview
Long context reasoning (AA-LCR)	74.3%	78.0%	Gemini 3 Flash Preview
DTBench	94.7%	89.1%	Gemini 3.5 Flash
LMCA	47.1%	43.1%	Gemini 3.5 Flash
Surface Evolver Bench	58.1%	Not measured	Only Gemini 3.5 Flash measured
LMArena Text	1482	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: instruction following	1467	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: creative writing	1470	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision	1308	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: English	1481	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: non-English	1475	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Chinese	1527	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: German	1494	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Japanese	1486	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Korean	1448	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: French	1490	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Spanish	1480	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Russian	1493	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: Polish	1516	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: multi-turn	1481	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: longer queries	1483	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: writing and language	1478	Not measured	Only Gemini 3.5 Flash measured
LMArena Text: entertainment and media	1459	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: English	1305	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: Chinese	1377	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: reading text	1317	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: humor	1321	Not measured	Only Gemini 3.5 Flash measured
LMArena Vision: creative writing	1301	Not measured	Only Gemini 3.5 Flash measured
LMArena Document	1463	Not measured	Only Gemini 3.5 Flash measured
EQ-Bench 4	1087	Not measured	Only Gemini 3.5 Flash measured
Neither model has a result on the other 14 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Gemini 3.5 Flash and Gemini 3 Flash Preview
Benchmark	Gemini 3.5 Flash	Gemini 3 Flash Preview	Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemini 3.5 Flash$0.0060Fits in one request

Gemini 3 Flash Preview$0.0020Fits in one request

Gemini 3 Flash Preview costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash$0.102Fits in one request

Gemini 3 Flash Preview$0.034Fits in one request

Gemini 3 Flash Preview costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash$0.390Fits in one request

Gemini 3 Flash Preview$0.130Fits in one request

Gemini 3 Flash Preview costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemini 3.5 Flash and Gemini 3 Flash Preview
Specification	Google Gemini 3.5 Flash	Google Gemini 3 Flash Preview
Maker	Google	Google
Weights	No public weights listed	No public weights listed
Released	May 19, 2026	December 17, 2025
Context window	1.05M	1.05M
Input $/Mtok	$1.50	$0.50
Output $/Mtok	$9.00	$3.00
Coding index	39.8	43.7
Independent measurements behind it	4	2
Cost per solved task	$1.21	$0.37
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.5 Flash better than Gemini 3 Flash Preview for coding?

Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash, though on 2 benchmarks against 4. Pick Gemini 3.5 Flash for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, Gemini 3.5 Flash or Gemini 3 Flash Preview?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, Gemini 3.5 Flash costs $1.21 and Gemini 3 Flash Preview $0.37.

Which has the bigger context window, Gemini 3.5 Flash or Gemini 3 Flash Preview?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.5 Flash vs Gemini 3 Flash Preview comparison based on?

57 benchmarks have a result for both models as of October 22, 2026. Gemini 3.5 Flash's coding index rests on 4 independent benchmarks and Gemini 3 Flash Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gemini-3-5-flash-vs-gemini-3-flash-preview" title="Gemini 3.5 Flash vs Gemini 3 Flash Preview, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gemini-3-5-flash-vs-gemini-3-flash-preview">LLMBenchmark.ai, Gemini 3.5 Flash vs Gemini 3 Flash Preview</a></p>

Gemini 3.5 Flash or Gemini 3 Flash Preview: which to pick

Which one for your work

Coding

Intelligence

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next