Enter opens the highlighted result. Esc closes.

Gemini 3.7 Flash vs Gemini 3.8 Flash

Gemini 3.8 Flash leads Gemini 3.7 Flash on coding, 61.6 to 58.0 on the Vibe Coding Index, at about the same output price ($3.75 vs $3.75 per million). Updated October 22, 2026; 113 benchmarks have a result for both.

Replace Gemini 3.7 Flash Replace Gemini 3.8 Flash
Gemini 3.7 FlashGoogle
Coding
58.0
Overall
65.7
Output $/M
$3.75
43
Gemini 3.8 FlashGoogle
Coding
61.6
Overall
69.0
Output $/M
$3.75
69
vs boards won of 113 shared, 1 tied

Gemini 3.7 Flash or Gemini 3.8 Flash: which to pick

Pick Gemini 3.8 Flash for coding: it scores 61.6 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash.

Pick Gemini 3.7 Flash for a lower cost per solved task ($1.78 against $2.74) and work measured by LMArena WebDev or SWE-bench Verified (Vals AI), where it leads.

Model AGemini 3.7 FlashGoogle58.0/1006 independent benchmarks$1.78 per solved taskModel BGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved task
Shared results
113
Gemini 3.7 Flash only
1
Gemini 3.8 Flash 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.

At a glance

Coding index
Gemini 3.7 Flash 58.0 from 6 benchmarks, Gemini 3.8 Flash 61.6 from 6 benchmarks.
Widest category
Math, 5.9 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: agents building Android apps: Gemini 3.7 Flash 1243 against Gemini 3.8 Flash 1078, 20.6 points apart on a 0 to 100 scale.
Output price
Both cost $3.75 per million output tokens.
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
CategoryGemini 3.7 FlashBarsGemini 3.8 FlashTies
Coding10121 tie
Intelligence11
Agentic work314
Reasoning213
Math33
Knowledge56
Web design72
General1218
All shared boards43691 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index1012
Coding benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
LiveBench coding80.5%82.2%Gemini 3.8 Flash
LMArena WebDev15911585Gemini 3.7 Flash
AA Coding Index71.576.3Gemini 3.8 Flash
LiveCodeBench (Vals AI)88.7%89.5%Gemini 3.8 Flash
SWE-bench Verified (Vals AI)80.8%80.0%Gemini 3.7 Flash
Terminal-Bench 4 (Vals AI)12.1%19.7%Gemini 3.8 Flash
Vibe Code Bench (Vals AI)70.4%78.7%Gemini 3.8 Flash
Code migration (Vals AI)34.8%36.5%Gemini 3.8 Flash
ProgramBench (Vals AI)0.0%1.0%Gemini 3.8 Flash
IOI (Vals AI)67.8%56.9%Gemini 3.7 Flash
Terminal-Bench 2.1 (Vals AI)77.5%81.3%Gemini 3.8 Flash
SWE-bench Multimodal (Vals AI)Not measured40.8%Only Gemini 3.8 Flash measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
SkillsBench (Vals AI)65.9%58.0%Gemini 3.7 Flash
CyberBench (Vals AI)43.8%43.8%Tie
SciCode59.8%56.6%Gemini 3.7 Flash
FrontierCode43.6%41.2%Gemini 3.7 Flash
FrontierSWE20.3%19.6%Gemini 3.7 Flash
WeirdMLNot measured84.8%Only Gemini 3.8 Flash measured
ALE-Bench904.31269.7Gemini 3.8 Flash
LMArena Text: coding14991508Gemini 3.8 Flash
LMArena Text: software and IT14981507Gemini 3.8 Flash
LMArena WebDev: React15871577Gemini 3.7 Flash
LMArena WebDev: HTML15931616Gemini 3.8 Flash
LMArena WebDev: from an image15991593Gemini 3.7 Flash
SciCode13.8%12.3%Gemini 3.7 Flash
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
AA Intelligence Index39.640.9Gemini 3.8 Flash
Epoch Capabilities Index158.0157.4Gemini 3.7 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index314
Agentic work benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
AA Agentic IndexNot measured40.2Only Gemini 3.8 Flash measured
Design Arena: agents building web apps12231238Gemini 3.8 Flash
Design Arena: agents building full-stack apps12081244Gemini 3.8 Flash
Design Arena: agents building mobile apps12291236Gemini 3.8 Flash
Design Arena: agents building Android apps12431078Gemini 3.7 Flash
Design Arena: agents building Godot games12641273Gemini 3.8 Flash
Design Arena: agents building games1235Not measuredOnly Gemini 3.7 Flash measured
Design Arena: PowerPoint slidesNot measured1153Only Gemini 3.8 Flash measured
Design Arena: spreadsheets10581022Gemini 3.7 Flash
LiveBench research76.5%79.1%Gemini 3.8 Flash
LiveBench browser56.0%64.0%Gemini 3.8 Flash
LiveBench long agentic28.3%30.1%Gemini 3.8 Flash
SREBench (Vals AI)4.6%11.1%Gemini 3.8 Flash
Finance Agent (Vals AI)59.0%61.4%Gemini 3.8 Flash
Tax Agent Bench (Vals AI)22.8%32.1%Gemini 3.8 Flash
Legal Research Bench (Vals AI)34.6%38.9%Gemini 3.8 Flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.1%Only Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)71.3%72.2%Gemini 3.8 Flash
BioMysteryBench (Vals AI)Not measured62.2%Only Gemini 3.8 Flash measured
Terminal-Bench-Science (Vals AI)7.1%8.6%Gemini 3.8 Flash
Vals Science IndexNot measured35.8%Only Gemini 3.8 Flash measured
Time Horizon Index (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
CUA-bench (Vals AI)Not measured4.2%Only Gemini 3.8 Flash measured
APEX-Agents67.8%64.3%Gemini 3.7 Flash
Remote Labor Index5.0%5.8%Gemini 3.8 Flash
Vending-Bench 2Not measured$5,094Only Gemini 3.8 Flash measured
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index213
Reasoning benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
GPQA Diamond93.9%94.4%Gemini 3.8 Flash
LiveBench reasoning87.8%89.3%Gemini 3.8 Flash
MysteryMechanism (Vals AI)Not measured36.5%Only Gemini 3.8 Flash measured
MMMU Pro (Vals AI)89.0%89.1%Gemini 3.8 Flash
GPQA Diamond (Artificial Analysis run)94.5%95.3%Gemini 3.8 Flash
Humanity's Last Exam (Artificial Analysis run)47.9%47.8%Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)94.8%95.4%Gemini 3.8 Flash
ARC-AGI95.5%98.5%Gemini 3.8 Flash
ARC-AGI-284.6%89.2%Gemini 3.8 Flash
Chess puzzles66.0%58.0%Gemini 3.7 Flash
Mystery game puzzles37.0%47.0%Gemini 3.8 Flash
LMArena Text: hard prompts14951509Gemini 3.8 Flash
LMArena Text: expert15121526Gemini 3.8 Flash
LMArena Text: hard prompts in English14871504Gemini 3.8 Flash
LMArena Vision: diagrams13291345Gemini 3.8 Flash
LMArena Vision: homework13201351Gemini 3.8 Flash
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
OTIS Mock AIME97.2%98.9%Gemini 3.8 Flash
FrontierMath, tiers 1 to 371.6%68.4%Gemini 3.7 Flash
FrontierMath, tier 436.6%22.0%Gemini 3.7 Flash
ProofBench58.0%48.0%Gemini 3.7 Flash
LMArena Text: math15111532Gemini 3.8 Flash
LMArena Text: mathematical work15021519Gemini 3.8 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index56
Knowledge benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
MMLU Pro90.1%90.2%Gemini 3.8 Flash
LegalBench (Vals AI)87.3%87.0%Gemini 3.7 Flash
TaxEval (Vals AI)74.7%74.5%Gemini 3.7 Flash
MortgageTax (Vals AI)66.7%65.3%Gemini 3.7 Flash
MedCode (Vals AI)53.4%48.1%Gemini 3.7 Flash
SimpleQA Verified69.2%69.7%Gemini 3.8 Flash
LMArena Text: science15111523Gemini 3.8 Flash
LMArena Text: medicine and healthcare14941508Gemini 3.8 Flash
LMArena Text: legal and government14961497Gemini 3.8 Flash
LMArena Text: business and finance14791479Gemini 3.8 Flash
FACTS Benchmark Suite71.2%69.4%Gemini 3.7 Flash
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index72
Web design benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
Design Arena: websites13031300Gemini 3.7 Flash
Design Arena: UI components12961316Gemini 3.8 Flash
Design Arena: game dev13171304Gemini 3.7 Flash
Design Arena: data viz13151270Gemini 3.7 Flash
Design Arena: 3D13071294Gemini 3.7 Flash
Design Arena: all code categories13081303Gemini 3.7 Flash
Design Arena: SVG12831296Gemini 3.8 Flash
Design Arena: ASCII art12761262Gemini 3.7 Flash
LiveBench design73.2%72.7%Gemini 3.7 Flash
GeneralLike-for-likePublic boards, shown as published, kept out of the index1218
General benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
Vals IndexNot measured56.0%Only Gemini 3.8 Flash measured
LiveBench data analysis68.0%54.0%Gemini 3.7 Flash
Public Benefits Bench (Vals AI)Not measured65.3%Only Gemini 3.8 Flash measured
SAGE (Vals AI)49.2%35.1%Gemini 3.7 Flash
MedScribe (Vals AI)83.9%84.5%Gemini 3.8 Flash
Long context reasoning (AA-LCR)83.0%84.0%Gemini 3.8 Flash
DTBench96.8%95.7%Gemini 3.7 Flash
LMCA50.4%52.9%Gemini 3.8 Flash
Surface Evolver BenchNot measured76.9%Only Gemini 3.8 Flash measured
Furniture assembly26.7%31.7%Gemini 3.8 Flash
LMArena Text14891499Gemini 3.8 Flash
LMArena Text: instruction following14841492Gemini 3.8 Flash
LMArena Text: creative writing14881488Gemini 3.7 Flash
LMArena Vision13141315Gemini 3.8 Flash
LMArena Text: English14831498Gemini 3.8 Flash
LMArena Text: non-English14871491Gemini 3.8 Flash
LMArena Text: Chinese15521553Gemini 3.8 Flash
LMArena Text: German15061501Gemini 3.7 Flash
LMArena Text: Japanese15111507Gemini 3.7 Flash
LMArena Text: Korean14811464Gemini 3.7 Flash
LMArena Text: French15001496Gemini 3.7 Flash
LMArena Text: Spanish14951487Gemini 3.7 Flash
LMArena Text: Russian15151514Gemini 3.7 Flash
LMArena Text: Polish15031497Gemini 3.7 Flash
LMArena Text: multi-turn14851503Gemini 3.8 Flash
LMArena Text: longer queries14921507Gemini 3.8 Flash
LMArena Text: writing and language14911494Gemini 3.8 Flash
LMArena Text: entertainment and media14771480Gemini 3.8 Flash
LMArena Vision: English13091318Gemini 3.8 Flash
LMArena Vision: Chinese13941416Gemini 3.8 Flash
LMArena Vision: reading text13221333Gemini 3.8 Flash
LMArena Vision: humor12991321Gemini 3.8 Flash
LMArena Vision: creative writing13121299Gemini 3.7 Flash
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.7 Flash and Gemini 3.8 Flash
BenchmarkGemini 3.7 FlashGemini 3.8 FlashLeader
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 3.7 Flash$0.0026Fits in one request
Gemini 3.8 Flash$0.0026Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Gemini 3.7 Flash$0.049Fits in one request
Gemini 3.8 Flash$0.049Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Gemini 3.7 Flash$0.188Fits in one request
Gemini 3.8 Flash$0.188Fits in one request

Same cost

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 3.7 Flash and Gemini 3.8 Flash
SpecificationGoogle Gemini 3.7 FlashGoogle Gemini 3.8 Flash
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedAugust 13, 2026September 2, 2026
Context window1.05M1.05M
Input $/Mtok$0.75$0.75
Output $/Mtok$3.75$3.75
Coding index58.061.6
Independent measurements behind it66
Cost per solved task$1.78$2.74
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.7 Flash better than Gemini 3.8 Flash for coding?

Pick Gemini 3.8 Flash for coding: it scores 61.6 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash. Pick Gemini 3.7 Flash for a lower cost per solved task ($1.78 against $2.74) and work measured by LMArena WebDev or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, Gemini 3.7 Flash or Gemini 3.8 Flash?

Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, Gemini 3.7 Flash costs $1.78 and Gemini 3.8 Flash $2.74.

Which has the bigger context window, Gemini 3.7 Flash or Gemini 3.8 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.7 Flash vs Gemini 3.8 Flash comparison based on?

113 benchmarks have a result for both models as of October 22, 2026. Gemini 3.7 Flash's coding index rests on 6 independent benchmarks and Gemini 3.8 Flash's on 6. 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-3-7-flash-vs-gemini-3-8-flash" title="Gemini 3.7 Flash vs Gemini 3.8 Flash, 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-3-7-flash-vs-gemini-3-8-flash">LLMBenchmark.ai, Gemini 3.7 Flash vs Gemini 3.8 Flash</a></p>