Gemini 3.1 Pro Preview vs Gemini 3.7 Flash

Updated October 21, 2026. 98 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.1 Pro Preview Replace Gemini 3.7 Flash

Gemini 3.1 Pro PreviewGoogle

Coding: 35.3
Overall: 29.7
Output $/M: $12.00

Gemini 3.7 FlashGoogle

Coding: 69.9
Overall: 39.6
Output $/M: $3.75

vs boards won of 98 shared, 2 tied

Decision reading

Pick Gemini 3.7 Flash for coding: it scores 69.9 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview when a solved task costs $0.99 against $1.78, or when what matters is ALE-Bench or GPQA Diamond, where it leads.

Model AGemini 3.1 Pro PreviewGoogle35.3/1001 independent benchmark$0.99 per solved task Model BGemini 3.7 FlashGoogle69.9/1002 independent benchmarks$1.78 per solved task

983314

Shared results: 98
Gemini 3.1 Pro Preview only: 33
Gemini 3.7 Flash only: 14
Like-for-like categories: 8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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, four public coding benchmarks
Gemini 3.7 Flash
Gemini 3.7 Flash scores 69.9 against 35.3.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 39.6 against 29.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 93.9%.
Same board, both measured
Math
AIME
No call
Only Gemini 3.1 Pro Preview has a AIME result, 98.1%.
Directional only
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 90.1%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 1304 against 1234.
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 3.7 Flash
Gemini 3.1 Pro Preview $0.0080, Gemini 3.7 Flash $0.0026 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview $0.99, Gemini 3.7 Flash $1.78.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.1 Pro Preview 35.3 from 1 benchmark, Gemini 3.7 Flash 69.9 from 2 benchmarks.
Widest category: Agentic work, 15.0 points apart on average over 13 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Gemini 3.1 Pro Preview 32.0% against Gemini 3.7 Flash 70.4%, 38.4 points apart on a 0 to 100 scale.
Output price: Gemini 3.1 Pro Preview $12.00 against Gemini 3.7 Flash $3.75 per million output tokens, 3.2x 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 3.1 Pro Preview	Gemini 3.7 Flash	Ties
Coding	1	15	1 tie
Intelligence	0	1
Agentic work	0	13
Reasoning	2	12
Math	0	6
Knowledge	5	5
Web design	1	7
General	5	23	1 tie
All shared boards	14	82	2 ties

CodingLike-for-likeFour of these boards feed the Vibe Coding Index115

Coding benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
LiveBench coding	Not measured	80.5%	Only Gemini 3.7 Flash measured
LMArena WebDev	1447	1591	Gemini 3.7 Flash
AA Coding Index	68.8	71.5	Gemini 3.7 Flash
LiveCodeBench (Vals AI)	88.5%	88.7%	Gemini 3.7 Flash
SWE-bench Verified (Vals AI)	78.8%	80.8%	Gemini 3.7 Flash
Terminal-Bench 4 (Vals AI)	2.5%	12.1%	Gemini 3.7 Flash
Vibe Code Bench (Vals AI)	32.0%	70.4%	Gemini 3.7 Flash
Code migration (Vals AI)	17.3%	34.8%	Gemini 3.7 Flash
ProgramBench (Vals AI)	0.0%	0.0%	Tie
IOI (Vals AI)	51.8%	67.8%	Gemini 3.7 Flash
Terminal-Bench 2.1 (Vals AI)	70.8%	77.5%	Gemini 3.7 Flash
Vibe Code Bench 1-100 (Vals AI)	6.7%	Not measured	Only Gemini 3.1 Pro Preview measured
SkillsBench (Vals AI)	Not measured	65.9%	Only Gemini 3.7 Flash measured
CyberBench (Vals AI)	Not measured	43.8%	Only Gemini 3.7 Flash measured
SciCode	58.7%	59.8%	Gemini 3.7 Flash
Terminal-Bench Hard (Artificial Analysis run)	53.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench	80.2%	Not measured	Only Gemini 3.1 Pro Preview measured
FrontierCode	Not measured	43.6%	Only Gemini 3.7 Flash measured
FrontierSWE	Not measured	20.3%	Only Gemini 3.7 Flash measured
GSO-Bench	22.6%	Not measured	Only Gemini 3.1 Pro Preview measured
WeirdML	72.1%	Not measured	Only Gemini 3.1 Pro Preview measured
MirrorCode	8.9%	Not measured	Only Gemini 3.1 Pro Preview measured
ALE-Bench	1160.6	904.3	Gemini 3.1 Pro Preview
LMArena Text: coding	1484	1499	Gemini 3.7 Flash
LMArena Text: software and IT	1487	1498	Gemini 3.7 Flash
LMArena WebDev: React	1438	1587	Gemini 3.7 Flash
LMArena WebDev: HTML	1490	1593	Gemini 3.7 Flash
LMArena WebDev: from an image	1481	1599	Gemini 3.7 Flash
Neither model has a result on the other 10 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01

Intelligence benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
AA Intelligence Index	29.7	39.6	Gemini 3.7 Flash
Epoch Capabilities Index	Not measured	158.0	Only Gemini 3.7 Flash measured

Agentic workLike-for-likePublic boards, shown as published, kept out of the index013

Agentic work benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
AA Agentic Index	8.2	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building web apps	1125	1224	Gemini 3.7 Flash
Design Arena: agents building full-stack apps	1068	1208	Gemini 3.7 Flash
Design Arena: agents building mobile apps	1094	1230	Gemini 3.7 Flash
Design Arena: agents building Android apps	1055	1247	Gemini 3.7 Flash
Design Arena: agents building Godot games	1236	1264	Gemini 3.7 Flash
Design Arena: agents building games	1114	1235	Gemini 3.7 Flash
Design Arena: HTML slides	1153	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slides	1064	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: spreadsheets	Not measured	1028	Only Gemini 3.7 Flash measured
LiveBench research	Not measured	76.5%	Only Gemini 3.7 Flash measured
LiveBench browser	Not measured	56.0%	Only Gemini 3.7 Flash measured
LiveBench long agentic	Not measured	28.3%	Only Gemini 3.7 Flash measured
SREBench (Vals AI)	0.0%	4.6%	Gemini 3.7 Flash
Finance Agent (Vals AI)	43.0%	59.0%	Gemini 3.7 Flash
Tax Agent Bench (Vals AI)	9.3%	22.8%	Gemini 3.7 Flash
Legal Research Bench (Vals AI)	20.7%	34.6%	Gemini 3.7 Flash
Excel Modeling Benchmark (Vals AI)	52.6%	71.3%	Gemini 3.7 Flash
BioMysteryBench (Vals AI)	60.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench-Science (Vals AI)	1.4%	7.1%	Gemini 3.7 Flash
Vals Science Index	27.4%	Not measured	Only Gemini 3.1 Pro Preview measured
τ²-Bench Telecom	95.6%	Not measured	Only Gemini 3.1 Pro Preview measured
APEX-Agents	35.1%	67.8%	Gemini 3.7 Flash
METR time horizons	77.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Remote Labor Index	Not measured	5.0%	Only Gemini 3.7 Flash measured
BALROG	57.0%	Not measured	Only Gemini 3.1 Pro Preview measured
DeepResearch Bench	47.8%	Not measured	Only Gemini 3.1 Pro Preview measured
PostTrainBench	22.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Vending-Bench 2	$911	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 10 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index212

Reasoning benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
GPQA Diamond	95.5%	93.9%	Gemini 3.1 Pro Preview
LiveBench reasoning	Not measured	87.8%	Only Gemini 3.7 Flash measured
MysteryMechanism (Vals AI)	20.7%	Not measured	Only Gemini 3.1 Pro Preview measured
MMMU Pro (Vals AI)	88.2%	89.0%	Gemini 3.7 Flash
GPQA Diamond (Artificial Analysis run)	94.1%	94.5%	Gemini 3.7 Flash
Humanity's Last Exam (Artificial Analysis run)	47.0%	47.9%	Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)	94.4%	94.8%	Gemini 3.7 Flash
ARC-AGI	98.0%	95.5%	Gemini 3.1 Pro Preview
ARC-AGI-2	77.1%	84.6%	Gemini 3.7 Flash
SimpleBench	79.6%	Not measured	Only Gemini 3.1 Pro Preview measured
Chess puzzles	51.0%	66.0%	Gemini 3.7 Flash
Mystery game puzzles	34.0%	37.0%	Gemini 3.7 Flash
EBR-bench	14.3%	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Text: hard prompts	1485	1495	Gemini 3.7 Flash
LMArena Text: expert	1483	1512	Gemini 3.7 Flash
LMArena Text: hard prompts in English	1480	1487	Gemini 3.7 Flash
LMArena Vision: diagrams	1311	1329	Gemini 3.7 Flash
LMArena Vision: homework	1316	1320	Gemini 3.7 Flash
Neither model has a result on the other 3 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index06

Math benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
AIME	98.1%	Not measured	Only Gemini 3.1 Pro Preview measured
OTIS Mock AIME	95.6%	97.2%	Gemini 3.7 Flash
FrontierMath, tiers 1 to 3	59.6%	71.6%	Gemini 3.7 Flash
FrontierMath, tier 4	26.8%	36.6%	Gemini 3.7 Flash
ProofBench	26.0%	58.0%	Gemini 3.7 Flash
LMArena Text: math	1486	1511	Gemini 3.7 Flash
LMArena Text: mathematical work	1478	1502	Gemini 3.7 Flash
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index55

Knowledge benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
MMLU Pro	91.0%	90.1%	Gemini 3.1 Pro Preview
LegalBench (Vals AI)	87.4%	87.3%	Gemini 3.1 Pro Preview
CaseLaw (Vals AI)	64.8%	Not measured	Only Gemini 3.1 Pro Preview measured
CorpFin (Vals AI)	64.5%	Not measured	Only Gemini 3.1 Pro Preview measured
TaxEval (Vals AI)	72.9%	74.7%	Gemini 3.7 Flash
MortgageTax (Vals AI)	69.4%	66.7%	Gemini 3.1 Pro Preview
MedQA (Vals AI)	96.4%	Not measured	Only Gemini 3.1 Pro Preview measured
MedCode (Vals AI)	59.1%	53.4%	Gemini 3.1 Pro Preview
SimpleQA Verified	73.5%	69.2%	Gemini 3.1 Pro Preview
LMArena Text: science	1497	1511	Gemini 3.7 Flash
LMArena Text: medicine and healthcare	1486	1494	Gemini 3.7 Flash
LMArena Text: legal and government	1487	1496	Gemini 3.7 Flash
LMArena Text: business and finance	1459	1479	Gemini 3.7 Flash
Neither model has a result on the other 4 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index17

Web design benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
Design Arena: websites	1234	1304	Gemini 3.7 Flash
Design Arena: UI components	1226	1299	Gemini 3.7 Flash
Design Arena: game dev	1203	1318	Gemini 3.7 Flash
Design Arena: data viz	1209	1315	Gemini 3.7 Flash
Design Arena: 3D	1234	1308	Gemini 3.7 Flash
Design Arena: all code categories	1231	1308	Gemini 3.7 Flash
Design Arena: SVG	1285	1283	Gemini 3.1 Pro Preview
Design Arena: ASCII art	1270	1276	Gemini 3.7 Flash
LiveBench design	Not measured	73.2%	Only Gemini 3.7 Flash measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index523

General benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	Leader
LiveBench data analysis	Not measured	68.0%	Only Gemini 3.7 Flash measured
Public Benefits Bench (Vals AI)	53.8%	Not measured	Only Gemini 3.1 Pro Preview measured
SAGE (Vals AI)	48.7%	49.2%	Gemini 3.7 Flash
MedScribe (Vals AI)	76.1%	83.9%	Gemini 3.7 Flash
Vals Multimodal Index	56.1%	Not measured	Only Gemini 3.1 Pro Preview measured
IFBench	77.1%	Not measured	Only Gemini 3.1 Pro Preview measured
Long context reasoning (AA-LCR)	82.0%	83.0%	Gemini 3.7 Flash
DTBench	97.1%	96.8%	Gemini 3.1 Pro Preview
LMCA	53.8%	50.4%	Gemini 3.1 Pro Preview
CL-bench	20.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Furniture assembly	26.7%	26.7%	Tie
ExploitBench	26.1%	Not measured	Only Gemini 3.1 Pro Preview measured
CL-bench Life	16.9%	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Text	1480	1489	Gemini 3.7 Flash
LMArena Text: instruction following	1466	1484	Gemini 3.7 Flash
LMArena Text: creative writing	1482	1488	Gemini 3.7 Flash
LMArena Vision	1296	1314	Gemini 3.7 Flash
LMArena Text: English	1478	1483	Gemini 3.7 Flash
LMArena Text: non-English	1476	1487	Gemini 3.7 Flash
LMArena Text: Chinese	1527	1552	Gemini 3.7 Flash
LMArena Text: German	1490	1506	Gemini 3.7 Flash
LMArena Text: Japanese	1491	1511	Gemini 3.7 Flash
LMArena Text: Korean	1455	1481	Gemini 3.7 Flash
LMArena Text: French	1487	1500	Gemini 3.7 Flash
LMArena Text: Spanish	1481	1495	Gemini 3.7 Flash
LMArena Text: Russian	1497	1515	Gemini 3.7 Flash
LMArena Text: Polish	1498	1503	Gemini 3.7 Flash
LMArena Text: multi-turn	1487	1485	Gemini 3.1 Pro Preview
LMArena Text: longer queries	1482	1492	Gemini 3.7 Flash
LMArena Text: writing and language	1481	1491	Gemini 3.7 Flash
LMArena Text: entertainment and media	1465	1477	Gemini 3.7 Flash
LMArena Vision: English	1287	1309	Gemini 3.7 Flash
LMArena Vision: Chinese	1364	1394	Gemini 3.7 Flash
LMArena Vision: reading text	1304	1322	Gemini 3.7 Flash
LMArena Vision: humor	1322	1299	Gemini 3.1 Pro Preview
LMArena Vision: captioning	1345	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things	1330	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Vision: creative writing	1324	1312	Gemini 3.1 Pro Preview
LMArena Document	1444	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 7 boards here

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

Image generation benchmarks for Gemini 3.1 Pro Preview and Gemini 3.7 Flash
Benchmark	Gemini 3.1 Pro Preview	Gemini 3.7 Flash	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 3.1 Pro Preview$0.0080Fits in one request

Gemini 3.7 Flash$0.0026Fits in one request

Gemini 3.7 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request

Gemini 3.7 Flash$0.049Fits in one request

Gemini 3.7 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits in one request

Gemini 3.7 Flash$0.188Fits in one request

Gemini 3.7 Flash 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 3.1 Pro Preview and Gemini 3.7 Flash
Specification	Google Gemini 3.1 Pro Preview	Google Gemini 3.7 Flash
Maker	Google	Google
Weights	No public weights listed	No public weights listed
Released	February 19, 2026	August 13, 2026
Context window	1.05M	1.05M
Input $/Mtok	$2.00	$0.75
Output $/Mtok	$12.00	$3.75
Coding index	35.3	69.9
Independent measurements behind it	1	2
Cost per solved task	$0.99	$1.78
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.1 Pro Preview better than Gemini 3.7 Flash for coding?

Pick Gemini 3.7 Flash for coding: it scores 69.9 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview when a solved task costs $0.99 against $1.78, or when what matters is ALE-Bench or GPQA Diamond, where it leads.

Which is cheaper, Gemini 3.1 Pro Preview or Gemini 3.7 Flash?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Gemini 3.7 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and Gemini 3.7 Flash $1.78.

Which has the bigger context window, Gemini 3.1 Pro Preview or Gemini 3.7 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.1 Pro Preview vs Gemini 3.7 Flash comparison based on?

98 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Pro Preview's coding index rests on 1 independent benchmark and Gemini 3.7 Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.

Decision reading

Which one for your work

Coding

Intelligence

Agentic work

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