Enter opens the highlighted result. Esc closes.

Gemini 3.8 Flash vs Gemini 4 Argon

Gemini 4 Argon leads Gemini 3.8 Flash on coding, 81.0 to 61.6 on the Vibe Coding Index, and Gemini 3.8 Flash costs 2.7x less per output token ($3.75 vs $10.00 per million). Updated October 22, 2026; 91 benchmarks have a result for both.

Replace Gemini 3.8 Flash Replace Gemini 4 Argon
Gemini 3.8 FlashGoogle
Coding
61.6
Overall
69.0
Output $/M
$3.75
2
Gemini 4 ArgonGoogle
Coding
81.0
Overall
84.0
Output $/M
$10.00
87
vs boards won of 91 shared, 2 tied

Gemini 3.8 Flash or Gemini 4 Argon: which to pick

Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 61.6 for Gemini 3.8 Flash, though on 5 benchmarks against 6.

Pick Gemini 3.8 Flash for output tokens 2.7x cheaper ($3.75 vs $10.00 per million) and work measured by Terminal-Bench 2.1 (Vals AI) or Long context reasoning (AA-LCR), where it leads.

Model AGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved taskModel BGemini 4 ArgonGoogle81.0/1005 independent benchmarksNo cost per solved task
Shared results
91
Gemini 3.8 Flash only
37
Gemini 4 Argon only
3
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 3.8 Flash 61.6 from 6 benchmarks, Gemini 4 Argon 81.0 from 5 benchmarks.
Widest category
Math, 22.2 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Gemini 3.8 Flash 22.0% against Gemini 4 Argon 78.0%, 56.1 points apart on a 0 to 100 scale.
Output price
Gemini 3.8 Flash $3.75 against Gemini 4 Argon $10.00 per million output tokens, 2.7x 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
CategoryGemini 3.8 FlashBarsGemini 4 ArgonTies
Coding1181 tie
Intelligence02
Agentic work017
Reasoning0101 tie
Math06
Knowledge07
Web design07
General120
All shared boards2872 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index118
Coding benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
LiveBench coding82.2%89.7%Gemini 4 Argon
LMArena WebDev15851678Gemini 4 Argon
AA Coding Index76.3Not measuredOnly Gemini 3.8 Flash measured
LiveCodeBench (Vals AI)89.5%Not measuredOnly Gemini 3.8 Flash measured
SWE-bench Verified (Vals AI)80.0%Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench 4 (Vals AI)19.7%57.6%Gemini 4 Argon
Vibe Code Bench (Vals AI)78.7%91.9%Gemini 4 Argon
Code migration (Vals AI)36.5%68.2%Gemini 4 Argon
ProgramBench (Vals AI)1.0%2.5%Gemini 4 Argon
IOI (Vals AI)56.9%100.0%Gemini 4 Argon
Terminal-Bench 2.1 (Vals AI)81.3%57.7%Gemini 3.8 Flash
SWE-bench Multimodal (Vals AI)40.8%56.0%Gemini 4 Argon
Vibe Code Bench 1-100 (Vals AI)18.8%21.2%Gemini 4 Argon
SkillsBench (Vals AI)58.0%Not measuredOnly Gemini 3.8 Flash measured
CyberBench (Vals AI)43.8%77.9%Gemini 4 Argon
SciCode56.6%61.8%Gemini 4 Argon
FrontierCode41.2%47.5%Gemini 4 Argon
FrontierSWE19.6%55.0%Gemini 4 Argon
WeirdML84.8%Not measuredOnly Gemini 3.8 Flash measured
MirrorCodeNot measured58.9%Only Gemini 4 Argon measured
ALE-Bench1269.72100.1Gemini 4 Argon
LMArena Text: coding15081546Gemini 4 Argon
LMArena Text: software and IT15071556Gemini 4 Argon
LMArena WebDev: React15771692Gemini 4 Argon
LMArena WebDev: HTML16161643Gemini 4 Argon
LMArena WebDev: from an image1593Not measuredOnly Gemini 3.8 Flash measured
SciCode12.3%12.3%Tie
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
AA Intelligence Index40.952.6Gemini 4 Argon
Epoch Capabilities Index157.4166.4Gemini 4 Argon
Agentic workLike-for-likePublic boards, shown as published, kept out of the index017
Agentic work benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
AA Agentic Index40.2Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building web apps1238Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building full-stack apps1244Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building mobile apps1236Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building Android apps1078Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building Godot games1273Not measuredOnly Gemini 3.8 Flash measured
Design Arena: PowerPoint slides1153Not measuredOnly Gemini 3.8 Flash measured
Design Arena: spreadsheets10221157Gemini 4 Argon
LiveBench research79.1%83.1%Gemini 4 Argon
LiveBench browser64.0%92.0%Gemini 4 Argon
LiveBench long agentic30.1%69.9%Gemini 4 Argon
SREBench (Vals AI)11.1%44.3%Gemini 4 Argon
Finance Agent (Vals AI)61.4%65.4%Gemini 4 Argon
Tax Agent Bench (Vals AI)32.1%44.6%Gemini 4 Argon
Legal Research Bench (Vals AI)38.9%54.8%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)12.1%27.1%Gemini 4 Argon
Excel Modeling Benchmark (Vals AI)72.2%75.2%Gemini 4 Argon
BioMysteryBench (Vals AI)62.2%76.3%Gemini 4 Argon
Terminal-Bench-Science (Vals AI)8.6%44.3%Gemini 4 Argon
Vals Science Index35.8%55.4%Gemini 4 Argon
Time Horizon Index (Vals AI)18.8%52.5%Gemini 4 Argon
CUA-bench (Vals AI)4.2%4.8%Gemini 4 Argon
Robo-bench (Vals AI)Not measured0.8%Only Gemini 4 Argon measured
APEX-Agents64.3%82.4%Gemini 4 Argon
Remote Labor Index5.8%Not measuredOnly Gemini 3.8 Flash measured
Vending-Bench 2$5,094$13,718Gemini 4 Argon
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
Reasoning benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
GPQA Diamond94.4%Not measuredOnly Gemini 3.8 Flash measured
LiveBench reasoning89.3%95.1%Gemini 4 Argon
MysteryMechanism (Vals AI)36.5%45.5%Gemini 4 Argon
MMMU Pro (Vals AI)89.1%Not measuredOnly Gemini 3.8 Flash measured
GPQA Diamond (Artificial Analysis run)95.3%Not measuredOnly Gemini 3.8 Flash measured
Humanity's Last Exam (Artificial Analysis run)47.8%57.1%Gemini 4 Argon
GPQA Diamond (Epoch AI run)95.4%96.4%Gemini 4 Argon
ARC-AGI98.5%98.5%Tie
ARC-AGI-289.2%91.3%Gemini 4 Argon
Chess puzzles58.0%59.0%Gemini 4 Argon
Mystery game puzzles47.0%64.0%Gemini 4 Argon
EBR-benchNot measured64.8%Only Gemini 4 Argon measured
LMArena Text: hard prompts15091546Gemini 4 Argon
LMArena Text: expert15261550Gemini 4 Argon
LMArena Text: hard prompts in English15041548Gemini 4 Argon
LMArena Vision: diagrams1345Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: homework1351Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
OTIS Mock AIME98.9%100.0%Gemini 4 Argon
FrontierMath, tiers 1 to 368.4%86.0%Gemini 4 Argon
FrontierMath, tier 422.0%78.0%Gemini 4 Argon
ProofBench48.0%99.0%Gemini 4 Argon
LMArena Text: math15321536Gemini 4 Argon
LMArena Text: mathematical work15191557Gemini 4 Argon
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index07
Knowledge benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
MMLU Pro90.2%Not measuredOnly Gemini 3.8 Flash measured
LegalBench (Vals AI)87.0%88.3%Gemini 4 Argon
TaxEval (Vals AI)74.5%Not measuredOnly Gemini 3.8 Flash measured
MortgageTax (Vals AI)65.3%Not measuredOnly Gemini 3.8 Flash measured
MedCode (Vals AI)48.1%58.8%Gemini 4 Argon
SimpleQA Verified69.7%76.0%Gemini 4 Argon
LMArena Text: science15231548Gemini 4 Argon
LMArena Text: medicine and healthcare15081555Gemini 4 Argon
LMArena Text: legal and government14971548Gemini 4 Argon
LMArena Text: business and finance14791525Gemini 4 Argon
FACTS Benchmark Suite69.4%Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
Design Arena: websites13001315Gemini 4 Argon
Design Arena: UI components13161333Gemini 4 Argon
Design Arena: game dev13041377Gemini 4 Argon
Design Arena: data viz12701332Gemini 4 Argon
Design Arena: 3D12941388Gemini 4 Argon
Design Arena: all code categories13031329Gemini 4 Argon
Design Arena: SVG1296Not measuredOnly Gemini 3.8 Flash measured
Design Arena: ASCII art1262Not measuredOnly Gemini 3.8 Flash measured
LiveBench design72.7%73.7%Gemini 4 Argon
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for Gemini 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
Vals Index56.0%69.2%Gemini 4 Argon
LiveBench data analysis54.0%85.2%Gemini 4 Argon
Public Benefits Bench (Vals AI)65.3%69.8%Gemini 4 Argon
SAGE (Vals AI)35.1%53.6%Gemini 4 Argon
MedScribe (Vals AI)84.5%87.4%Gemini 4 Argon
Long context reasoning (AA-LCR)84.0%79.7%Gemini 3.8 Flash
DTBench95.7%97.6%Gemini 4 Argon
LMCA52.9%63.7%Gemini 4 Argon
Surface Evolver Bench76.9%Not measuredOnly Gemini 3.8 Flash measured
Furniture assembly31.7%72.5%Gemini 4 Argon
LMArena Text14991532Gemini 4 Argon
LMArena Text: instruction following14921534Gemini 4 Argon
LMArena Text: creative writing14881527Gemini 4 Argon
LMArena Vision1315Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: English14981538Gemini 4 Argon
LMArena Text: non-English14911522Gemini 4 Argon
LMArena Text: Chinese15531611Gemini 4 Argon
LMArena Text: German1501Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Japanese1507Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Korean1464Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: French1496Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Spanish14871503Gemini 4 Argon
LMArena Text: Russian15141534Gemini 4 Argon
LMArena Text: Polish1497Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: multi-turn15031556Gemini 4 Argon
LMArena Text: longer queries15071547Gemini 4 Argon
LMArena Text: writing and language14941529Gemini 4 Argon
LMArena Text: entertainment and media14801527Gemini 4 Argon
LMArena Vision: English1318Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: Chinese1416Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: reading text1333Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: humor1321Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: creative writing1299Not measuredOnly Gemini 3.8 Flash measured
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 3.8 Flash and Gemini 4 Argon
BenchmarkGemini 3.8 FlashGemini 4 ArgonLeader
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 3.8 Flash$0.0026Fits in one request
Gemini 4 Argon$0.0070Fits in one request

Gemini 3.8 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.8 Flash$0.049Fits in one request
Gemini 4 Argon$0.130Fits in one request

Gemini 3.8 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.8 Flash$0.188Fits in one request
Gemini 4 Argon$0.500Fits in one request

Gemini 3.8 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 3.8 Flash and Gemini 4 Argon
SpecificationGoogle Gemini 3.8 FlashGoogle Gemini 4 Argon
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 2, 2026October 13, 2026
Context window1.05M1.05M
Input $/Mtok$0.75$2.00
Output $/Mtok$3.75$10.00
Coding index61.681.0
Independent measurements behind it65
Cost per solved task$2.74Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.8 Flash better than Gemini 4 Argon for coding?

Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 61.6 for Gemini 3.8 Flash, though on 5 benchmarks against 6. Pick Gemini 3.8 Flash for output tokens 2.7x cheaper ($3.75 vs $10.00 per million) and work measured by Terminal-Bench 2.1 (Vals AI) or Long context reasoning (AA-LCR), where it leads.

Which is cheaper, Gemini 3.8 Flash or Gemini 4 Argon?

Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. Cost per solved task is known for Gemini 3.8 Flash only.

Which has the bigger context window, Gemini 3.8 Flash or Gemini 4 Argon?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.8 Flash vs Gemini 4 Argon comparison based on?

91 benchmarks have a result for both models as of October 22, 2026. Gemini 3.8 Flash's coding index rests on 6 independent benchmarks and Gemini 4 Argon's on 5. 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-3-8-flash-vs-gemini-4-argon" title="Gemini 3.8 Flash vs Gemini 4 Argon, 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-3-8-flash-vs-gemini-4-argon">LLMBenchmark.ai, Gemini 3.8 Flash vs Gemini 4 Argon</a></p>