Enter opens the highlighted result. Esc closes.

Gemini 3.6 Flash vs Qwen3.5 397B A17B

Gemini 3.6 Flash leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 34.0 to 21.4, and Qwen3.5 397B A17B costs 1.6x less per output token ($2.34 vs $3.75 per million). Updated October 22, 2026; 59 benchmarks have a result for both.

Replace Gemini 3.6 Flash Replace Qwen3.5 397B A17B
Gemini 3.6 FlashGoogle
Coding
62.5
Overall
68.3
Output $/M
$3.75
59
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
0
vs boards won of 59 shared

Gemini 3.6 Flash or Qwen3.5 397B A17B: which to pick

Only Gemini 3.6 Flash has a coding score, 62.5 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding.

Pick Qwen3.5 397B A17B for output tokens 1.6x cheaper ($2.34 vs $3.75 per million).

Model AGemini 3.6 FlashGoogle62.5/1004 independent benchmarks$1.49 per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
59
Gemini 3.6 Flash only
50
Qwen3.5 397B A17B only
6
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 3.6 Flash 62.5 from 4 benchmarks, Qwen3.5 397B A17B not benchmarked.
Widest category
Agentic work, 22.0 points apart on average over 1 shared benchmark.
Widest single gap
FrontierMath, tiers 1 to 3: Gemini 3.6 Flash 58.9% against Qwen3.5 397B A17B 31.2%, 27.7 points apart on a 0 to 100 scale.
Output price
Gemini 3.6 Flash $3.75 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.6x apart.
Context window
Gemini 3.6 Flash takes 1.05M tokens, Qwen3.5 397B A17B 262K.

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 3.6 FlashBarsQwen3.5 397B A17BTies
Coding70
Intelligence20
Agentic work10
Reasoning90
Math40
Knowledge40
Web design60
General260
All shared boards590
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
LMArena WebDev15381400Gemini 3.6 Flash
AA Coding Index69.2Not measuredOnly Gemini 3.6 Flash measured
LiveCodeBench (Vals AI)88.1%Not measuredOnly Gemini 3.6 Flash measured
SWE-bench Verified (Vals AI)79.6%Not measuredOnly Gemini 3.6 Flash measured
Vibe Code Bench (Vals AI)64.0%Not measuredOnly Gemini 3.6 Flash measured
Code migration (Vals AI)30.9%Not measuredOnly Gemini 3.6 Flash measured
ProgramBench (Vals AI)0.0%Not measuredOnly Gemini 3.6 Flash measured
IOI (Vals AI)35.1%Not measuredOnly Gemini 3.6 Flash measured
Terminal-Bench 2.1 (Vals AI)73.8%Not measuredOnly Gemini 3.6 Flash measured
CyberBench (Vals AI)45.4%Not measuredOnly Gemini 3.6 Flash measured
SciCode53.4%44.8%Gemini 3.6 Flash
Terminal-Bench Hard (Artificial Analysis run)Not measured40.9%Only Qwen3.5 397B A17B measured
FrontierCode34.4%Not measuredOnly Gemini 3.6 Flash measured
WeirdML56.1%Not measuredOnly Gemini 3.6 Flash measured
ALE-Bench715.5621.9Gemini 3.6 Flash
LMArena Text: coding14911464Gemini 3.6 Flash
LMArena Text: software and IT14921463Gemini 3.6 Flash
LMArena WebDev: React15281388Gemini 3.6 Flash
LMArena WebDev: HTML15471410Gemini 3.6 Flash
LMArena WebDev: from an image1545Not measuredOnly Gemini 3.6 Flash measured
SciCode10.8%Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
AA Intelligence Index34.021.4Gemini 3.6 Flash
Epoch Capabilities Index154.5146.8Gemini 3.6 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
AA Agentic Index29.0Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building web apps1197Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building full-stack apps1181Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building mobile apps1198Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building Android apps1204Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building games1180Not measuredOnly Gemini 3.6 Flash measured
Design Arena: HTML slides1099Not measuredOnly Gemini 3.6 Flash measured
Design Arena: PowerPoint slides1121Not measuredOnly Gemini 3.6 Flash measured
Design Arena: spreadsheets1071Not measuredOnly Gemini 3.6 Flash measured
Finance Agent (Vals AI)56.3%Not measuredOnly Gemini 3.6 Flash measured
Tax Agent Bench (Vals AI)18.0%Not measuredOnly Gemini 3.6 Flash measured
Legal Research Bench (Vals AI)25.0%Not measuredOnly Gemini 3.6 Flash measured
Excel Modeling Benchmark (Vals AI)65.4%Not measuredOnly Gemini 3.6 Flash measured
BioMysteryBench (Vals AI)58.5%Not measuredOnly Gemini 3.6 Flash measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Gemini 3.6 Flash measured
τ²-Bench TelecomNot measured95.6%Only Qwen3.5 397B A17B measured
APEX-Agents46.9%24.9%Gemini 3.6 Flash
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
GPQA Diamond93.4%Not measuredOnly Gemini 3.6 Flash measured
MMMU Pro (Vals AI)88.4%Not measuredOnly Gemini 3.6 Flash measured
GPQA Diamond (Artificial Analysis run)92.8%89.3%Gemini 3.6 Flash
Humanity's Last Exam (Artificial Analysis run)40.8%29.0%Gemini 3.6 Flash
GPQA Diamond (Epoch AI run)94.1%86.4%Gemini 3.6 Flash
ARC-AGI91.2%Not measuredOnly Gemini 3.6 Flash measured
ARC-AGI-260.4%Not measuredOnly Gemini 3.6 Flash measured
Chess puzzles42.0%Not measuredOnly Gemini 3.6 Flash measured
Mystery game puzzles30.0%18.0%Gemini 3.6 Flash
LMArena Text: hard prompts14861448Gemini 3.6 Flash
LMArena Text: expert14901462Gemini 3.6 Flash
LMArena Text: hard prompts in English14841450Gemini 3.6 Flash
LMArena Vision: diagrams13141277Gemini 3.6 Flash
LMArena Vision: homework13141292Gemini 3.6 Flash
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
OTIS Mock AIME94.2%88.9%Gemini 3.6 Flash
FrontierMath, tiers 1 to 358.9%31.2%Gemini 3.6 Flash
FrontierMath, tier 422.0%Not measuredOnly Gemini 3.6 Flash measured
ProofBench36.0%Not measuredOnly Gemini 3.6 Flash measured
LMArena Text: math15081453Gemini 3.6 Flash
LMArena Text: mathematical work14921454Gemini 3.6 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
MMLU Pro89.3%Not measuredOnly Gemini 3.6 Flash measured
LegalBench (Vals AI)86.7%Not measuredOnly Gemini 3.6 Flash measured
CorpFin (Vals AI)63.3%Not measuredOnly Gemini 3.6 Flash measured
TaxEval (Vals AI)74.9%Not measuredOnly Gemini 3.6 Flash measured
MortgageTax (Vals AI)67.6%Not measuredOnly Gemini 3.6 Flash measured
MedCode (Vals AI)53.1%Not measuredOnly Gemini 3.6 Flash measured
SimpleQA Verified66.2%Not measuredOnly Gemini 3.6 Flash measured
LMArena Text: science14891457Gemini 3.6 Flash
LMArena Text: medicine and healthcare14691455Gemini 3.6 Flash
LMArena Text: legal and government14791441Gemini 3.6 Flash
LMArena Text: business and finance14641435Gemini 3.6 Flash
FACTS Benchmark Suite65.3%Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
Design Arena: websites13001190Gemini 3.6 Flash
Design Arena: UI components12941160Gemini 3.6 Flash
Design Arena: game dev12631140Gemini 3.6 Flash
Design Arena: data viz12891175Gemini 3.6 Flash
Design Arena: 3D12711160Gemini 3.6 Flash
Design Arena: all code categories12891179Gemini 3.6 Flash
Design Arena: SVGNot measured1139Only Qwen3.5 397B A17B measured
Design Arena: ASCII art1281Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index260
General benchmarks for Gemini 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
Public Benefits Bench (Vals AI)56.6%Not measuredOnly Gemini 3.6 Flash measured
SAGE (Vals AI)48.7%Not measuredOnly Gemini 3.6 Flash measured
MedScribe (Vals AI)79.7%Not measuredOnly Gemini 3.6 Flash measured
Vals Multimodal Index65.1%Not measuredOnly Gemini 3.6 Flash measured
IFBenchNot measured78.8%Only Qwen3.5 397B A17B measured
Long context reasoning (AA-LCR)80.0%77.3%Gemini 3.6 Flash
DTBench95.5%87.5%Gemini 3.6 Flash
LMCA44.9%37.9%Gemini 3.6 Flash
Furniture assembly23.3%Not measuredOnly Gemini 3.6 Flash measured
LMArena Text14801437Gemini 3.6 Flash
LMArena Text: instruction following14671424Gemini 3.6 Flash
LMArena Text: creative writing14661402Gemini 3.6 Flash
LMArena Vision12991262Gemini 3.6 Flash
LMArena Text: English14821443Gemini 3.6 Flash
LMArena Text: non-English14701430Gemini 3.6 Flash
LMArena Text: Chinese15311498Gemini 3.6 Flash
LMArena Text: German14801445Gemini 3.6 Flash
LMArena Text: Japanese14751429Gemini 3.6 Flash
LMArena Text: Korean14291384Gemini 3.6 Flash
LMArena Text: French15031462Gemini 3.6 Flash
LMArena Text: Spanish14761441Gemini 3.6 Flash
LMArena Text: Russian14881430Gemini 3.6 Flash
LMArena Text: Polish14731447Gemini 3.6 Flash
LMArena Text: multi-turn14811446Gemini 3.6 Flash
LMArena Text: longer queries14751441Gemini 3.6 Flash
LMArena Text: writing and language14701415Gemini 3.6 Flash
LMArena Text: entertainment and media14561399Gemini 3.6 Flash
LMArena Vision: English12951268Gemini 3.6 Flash
LMArena Vision: Chinese13571314Gemini 3.6 Flash
LMArena Vision: reading text13121271Gemini 3.6 Flash
LMArena Vision: humor12891262Gemini 3.6 Flash
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writing12781260Gemini 3.6 Flash
LMArena Document1456Not measuredOnly Gemini 3.6 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 3.6 Flash and Qwen3.5 397B A17B
BenchmarkGemini 3.6 FlashQwen3.5 397B A17BLeader
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 3.6 Flash$0.0026Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

Qwen3.5 397B A17B costs less

Repository review

50K input + 3K output tokens

Gemini 3.6 Flash$0.049Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

Qwen3.5 397B A17B costs less

Agent loop

200K input + 10K output tokens

Gemini 3.6 Flash$0.188Fits in one request
Qwen3.5 397B A17B$0.101Fits in one request

Qwen3.5 397B A17B 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 3.6 Flash and Qwen3.5 397B A17B
SpecificationGoogle Gemini 3.6 FlashQwen3.5 397B A17B
MakerGoogleQwen
WeightsNo public weights listedOpen weights
ReleasedJuly 21, 2026February 16, 2026
Context window1.05M262K
Input $/Mtok$0.75$0.39
Output $/Mtok$3.75$2.34
Coding index62.5Not benchmarked
Independent measurements behind it41
Cost per solved task$1.49Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.6 Flash better than Qwen3.5 397B A17B for coding?

Only Gemini 3.6 Flash has a coding score, 62.5 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for output tokens 1.6x cheaper ($2.34 vs $3.75 per million).

Which is cheaper, Gemini 3.6 Flash or Qwen3.5 397B A17B?

Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for Gemini 3.6 Flash only.

Which has the bigger context window, Gemini 3.6 Flash or Qwen3.5 397B A17B?

Gemini 3.6 Flash, with 1.05M tokens against 262K.

How many benchmarks is the Gemini 3.6 Flash vs Qwen3.5 397B A17B comparison based on?

59 benchmarks have a result for both models as of October 22, 2026. Gemini 3.6 Flash's coding index rests on 4 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next