LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash vs Qwen3.8 Max (0902)

Updated October 21, 2026. 95 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.5 Flash Replace Qwen3.8 Max (0902)
Gemini 3.5 FlashGoogle
Coding
42.8
Overall
33.6
Output $/M
$9.00
26
Qwen3.8 Max (0902)Qwen
Coding
63.5
Overall
45.4
Output $/M
$6.00
68
vs boards won of 95 shared, 1 tied

Decision reading

Pick Qwen3.8 Max (0902) for coding: it scores 63.5 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash.

Pick Gemini 3.5 Flash when a solved task costs $1.21 against $1.32, or when the context window is larger, 1.05M against 1M tokens.

Model AGemini 3.5 FlashGoogle42.8/1001 independent benchmark$1.21 per solved taskModel BQwen3.8 Max (0902)Qwen63.5/1002 independent benchmarks$1.32 per solved task
Shared results
95
Gemini 3.5 Flash only
15
Qwen3.8 Max (0902) only
18
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.

At a glance

Coding index
Gemini 3.5 Flash 42.8 from 1 benchmark, Qwen3.8 Max (0902) 63.5 from 2 benchmarks.
Widest category
Agentic work, 11.8 points apart on average over 12 shared benchmarks.
Widest single gap
APEX-Agents: Gemini 3.5 Flash 27.5% against Qwen3.8 Max (0902) 63.3%, 35.8 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash $9.00 against Qwen3.8 Max (0902) $6.00 per million output tokens, 1.5x apart.
Context window
Gemini 3.5 Flash takes 1.05M tokens, Qwen3.8 Max (0902) 1M.

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 3.5 FlashBarsQwen3.8 Max (0902)Ties
Coding4101 tie
Intelligence02
Agentic work210
Reasoning39
Math24
Knowledge47
Web design16
General1020
All shared boards26681 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index410
Coding benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
LiveBench codingNot measured60.3%Only Qwen3.8 Max (0902) measured
LMArena WebDev14991674Qwen3.8 Max (0902)
AA Coding IndexNot measured76.2Only Qwen3.8 Max (0902) measured
LiveCodeBench (Vals AI)87.6%87.8%Qwen3.8 Max (0902)
SWE-bench Verified (Vals AI)78.8%85.6%Qwen3.8 Max (0902)
Terminal-Bench 4 (Vals AI)6.1%34.3%Qwen3.8 Max (0902)
Vibe Code Bench (Vals AI)48.7%64.7%Qwen3.8 Max (0902)
Code migration (Vals AI)26.8%24.0%Gemini 3.5 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured68.9%Only Qwen3.8 Max (0902) measured
Terminal-Bench 2.1 (Vals AI)74.2%67.4%Gemini 3.5 Flash
SWE-bench Multimodal (Vals AI)Not measured42.5%Only Qwen3.8 Max (0902) measured
Vibe Code Bench 1-100 (Vals AI)Not measured12.8%Only Qwen3.8 Max (0902) measured
SkillsBench (Vals AI)52.7%42.0%Gemini 3.5 Flash
CyberBench (Vals AI)Not measured28.6%Only Qwen3.8 Max (0902) measured
SciCode53.9%53.2%Gemini 3.5 Flash
Terminal-Bench Hard (Artificial Analysis run)46.2%Not measuredOnly Gemini 3.5 Flash measured
FrontierSWENot measured17.8%Only Qwen3.8 Max (0902) measured
WeirdML62.6%Not measuredOnly Gemini 3.5 Flash measured
ALE-Bench911.0Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: coding14931502Qwen3.8 Max (0902)
LMArena Text: software and IT14941498Qwen3.8 Max (0902)
LMArena WebDev: React14951692Qwen3.8 Max (0902)
LMArena WebDev: HTML15221649Qwen3.8 Max (0902)
LMArena WebDev: from an image15041637Qwen3.8 Max (0902)
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
AA Intelligence Index33.645.4Qwen3.8 Max (0902)
Epoch Capabilities Index154.9157.4Qwen3.8 Max (0902)
Agentic workLike-for-likePublic boards, shown as published, kept out of the index210
Agentic work benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
AA Agentic IndexNot measured56.0Only Qwen3.8 Max (0902) measured
Design Arena: agents building web apps12021301Qwen3.8 Max (0902)
Design Arena: agents building full-stack apps11971305Qwen3.8 Max (0902)
Design Arena: agents building mobile apps11751223Qwen3.8 Max (0902)
Design Arena: agents building Android apps11901207Qwen3.8 Max (0902)
Design Arena: agents building Godot games10981234Qwen3.8 Max (0902)
Design Arena: agents building games1180Not measuredOnly Gemini 3.5 Flash measured
Design Arena: HTML slides1142Not measuredOnly Gemini 3.5 Flash measured
Design Arena: PowerPoint slides11781257Qwen3.8 Max (0902)
Design Arena: spreadsheetsNot measured868Only Qwen3.8 Max (0902) measured
LiveBench researchNot measured69.9%Only Qwen3.8 Max (0902) measured
LiveBench browserNot measured32.0%Only Qwen3.8 Max (0902) measured
LiveBench long agenticNot measured42.3%Only Qwen3.8 Max (0902) measured
Finance Agent (Vals AI)57.9%50.6%Gemini 3.5 Flash
Tax Agent Bench (Vals AI)21.6%32.1%Qwen3.8 Max (0902)
Legal Research Bench (Vals AI)30.8%47.6%Qwen3.8 Max (0902)
Excel Modeling Benchmark (Vals AI)63.5%60.1%Gemini 3.5 Flash
Terminal-Bench-Science (Vals AI)5.7%12.9%Qwen3.8 Max (0902)
τ²-Bench Telecom95.6%Not measuredOnly Gemini 3.5 Flash measured
APEX-Agents27.5%63.3%Qwen3.8 Max (0902)
Vending-Bench 2$5,396Not measuredOnly Gemini 3.5 Flash measured
LMArena SearchNot measured1261Only Qwen3.8 Max (0902) measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index39
Reasoning benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
GPQA Diamond92.7%93.7%Qwen3.8 Max (0902)
LiveBench reasoningNot measured88.2%Only Qwen3.8 Max (0902) measured
MysteryMechanism (Vals AI)Not measured23.9%Only Qwen3.8 Max (0902) measured
MMMU Pro (Vals AI)88.3%88.0%Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)92.2%92.8%Qwen3.8 Max (0902)
Humanity's Last Exam (Artificial Analysis run)42.7%43.1%Qwen3.8 Max (0902)
GPQA Diamond (Epoch AI run)92.8%92.7%Gemini 3.5 Flash
ARC-AGI92.5%Not measuredOnly Gemini 3.5 Flash measured
ARC-AGI-272.1%Not measuredOnly Gemini 3.5 Flash measured
SimpleBench76.7%Not measuredOnly Gemini 3.5 Flash measured
Chess puzzles45.0%46.0%Qwen3.8 Max (0902)
Mystery game puzzles32.0%38.0%Qwen3.8 Max (0902)
EBR-bench4.8%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: hard prompts14881496Qwen3.8 Max (0902)
LMArena Text: expert14951507Qwen3.8 Max (0902)
LMArena Text: hard prompts in English14831503Qwen3.8 Max (0902)
LMArena Vision: diagrams13231323Gemini 3.5 Flash
LMArena Vision: homework13301336Qwen3.8 Max (0902)
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
OTIS Mock AIME95.6%100.0%Qwen3.8 Max (0902)
FrontierMath, tiers 1 to 362.8%74.7%Qwen3.8 Max (0902)
FrontierMath, tier 426.8%46.3%Qwen3.8 Max (0902)
ProofBench31.0%58.0%Qwen3.8 Max (0902)
LMArena Text: math15041501Gemini 3.5 Flash
LMArena Text: mathematical work14951491Gemini 3.5 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index47
Knowledge benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
MMLU Pro89.5%88.6%Gemini 3.5 Flash
LegalBench (Vals AI)83.6%83.6%Qwen3.8 Max (0902)
CorpFin (Vals AI)64.7%65.8%Qwen3.8 Max (0902)
TaxEval (Vals AI)74.4%75.5%Qwen3.8 Max (0902)
MortgageTax (Vals AI)68.1%64.0%Gemini 3.5 Flash
MedCode (Vals AI)55.8%40.7%Gemini 3.5 Flash
SimpleQA Verified66.2%47.3%Gemini 3.5 Flash
LMArena Text: science14951512Qwen3.8 Max (0902)
LMArena Text: medicine and healthcare14831503Qwen3.8 Max (0902)
LMArena Text: legal and government14881492Qwen3.8 Max (0902)
LMArena Text: business and finance14671480Qwen3.8 Max (0902)
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index16
Web design benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
Design Arena: websites12681275Qwen3.8 Max (0902)
Design Arena: UI components12721340Qwen3.8 Max (0902)
Design Arena: game dev12631313Qwen3.8 Max (0902)
Design Arena: data viz12361281Qwen3.8 Max (0902)
Design Arena: 3D12441337Qwen3.8 Max (0902)
Design Arena: all code categories12661293Qwen3.8 Max (0902)
Design Arena: SVG1254Not measuredOnly Gemini 3.5 Flash measured
Design Arena: ASCII art12531201Gemini 3.5 Flash
LiveBench designNot measured78.6%Only Qwen3.8 Max (0902) measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1020
General benchmarks for Gemini 3.5 Flash and Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)Leader
LiveBench data analysisNot measured78.4%Only Qwen3.8 Max (0902) measured
Public Benefits Bench (Vals AI)59.5%67.1%Qwen3.8 Max (0902)
SAGE (Vals AI)49.9%51.2%Qwen3.8 Max (0902)
MedScribe (Vals AI)76.6%85.0%Qwen3.8 Max (0902)
Vals Multimodal Index62.9%65.4%Qwen3.8 Max (0902)
IFBench76.3%Not measuredOnly Gemini 3.5 Flash measured
Long context reasoning (AA-LCR)74.3%80.3%Qwen3.8 Max (0902)
DTBench94.7%92.0%Gemini 3.5 Flash
LMCA47.1%46.2%Gemini 3.5 Flash
Surface Evolver Bench58.1%Not measuredOnly Gemini 3.5 Flash measured
Furniture assemblyNot measured20.0%Only Qwen3.8 Max (0902) measured
LMArena Text14821483Qwen3.8 Max (0902)
LMArena Text: instruction following14671481Qwen3.8 Max (0902)
LMArena Text: creative writing14701477Qwen3.8 Max (0902)
LMArena Vision13081313Qwen3.8 Max (0902)
LMArena Text: English14811491Qwen3.8 Max (0902)
LMArena Text: non-English14751473Gemini 3.5 Flash
LMArena Text: Chinese15271539Qwen3.8 Max (0902)
LMArena Text: German14941478Gemini 3.5 Flash
LMArena Text: Japanese14861473Gemini 3.5 Flash
LMArena Text: Korean14481460Qwen3.8 Max (0902)
LMArena Text: French14901498Qwen3.8 Max (0902)
LMArena Text: Spanish14801489Qwen3.8 Max (0902)
LMArena Text: Russian14931482Gemini 3.5 Flash
LMArena Text: Polish15161471Gemini 3.5 Flash
LMArena Text: multi-turn14811489Qwen3.8 Max (0902)
LMArena Text: longer queries14831488Qwen3.8 Max (0902)
LMArena Text: writing and language14781477Gemini 3.5 Flash
LMArena Text: entertainment and media14591464Qwen3.8 Max (0902)
LMArena Vision: English13051311Qwen3.8 Max (0902)
LMArena Vision: Chinese13771358Gemini 3.5 Flash
LMArena Vision: reading text13171322Qwen3.8 Max (0902)
LMArena Vision: humor13211304Gemini 3.5 Flash
LMArena Vision: creative writing13011312Qwen3.8 Max (0902)
LMArena Document1463Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 11 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 Qwen3.8 Max (0902)
BenchmarkGemini 3.5 FlashQwen3.8 Max (0902)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
Qwen3.8 Max (0902)$0.0050Fits in one request

Qwen3.8 Max (0902) costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash$0.102Fits in one request
Qwen3.8 Max (0902)$0.118Fits in one request

Gemini 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash$0.390Fits in one request
Qwen3.8 Max (0902)$0.460Fits in one request

Gemini 3.5 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 3.5 Flash and Qwen3.8 Max (0902)
SpecificationGoogle Gemini 3.5 FlashQwen3.8 Max (0902)
MakerGoogleQwen
WeightsNo public weights listedNo public weights listed
ReleasedMay 19, 2026September 3, 2026
Context window1.05M1M
Input $/Mtok$1.50$2.00
Output $/Mtok$9.00$6.00
Coding index42.863.5
Independent measurements behind it12
Cost per solved task$1.21$1.32
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash better than Qwen3.8 Max (0902) for coding?

Pick Qwen3.8 Max (0902) for coding: it scores 63.5 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash. Pick Gemini 3.5 Flash when a solved task costs $1.21 against $1.32, or when the context window is larger, 1.05M against 1M tokens.

Which is cheaper, Gemini 3.5 Flash or Qwen3.8 Max (0902)?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Qwen3.8 Max (0902) costs $2.00 and $6.00. Per solved SWE-bench Verified task, Gemini 3.5 Flash costs $1.21 and Qwen3.8 Max (0902) $1.32.

Which has the bigger context window, Gemini 3.5 Flash or Qwen3.8 Max (0902)?

Gemini 3.5 Flash, with 1.05M tokens against 1M.

How many benchmarks is the Gemini 3.5 Flash vs Qwen3.8 Max (0902) comparison based on?

95 benchmarks have a result for both models as of October 21, 2026. Gemini 3.5 Flash's coding index rests on 1 independent benchmark and Qwen3.8 Max (0902)'s on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next