LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Qwen3.5 397B A17B vs Hy3 preview

Updated October 21, 2026. 34 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Qwen3.5 397B A17B Replace Hy3 preview
Qwen3.5 397B A17BQwen
Coding
28.6
Overall
21.4
Output $/M
$2.34
33
Hy3 previewTencent
Coding
22.4
Overall
25.3
Output $/M
$0.60
1
vs boards won of 34 shared

Decision reading

Pick Qwen3.5 397B A17B for coding: it scores 28.6 on the Vibe Coding Index against 22.4 for Hy3 preview.

Pick Hy3 preview when output tokens cost 3.9x less, or when the benchmark that matters is AA Intelligence Index, where it leads.

Model AQwen3.5 397B A17BQwen28.6/1001 independent benchmarkNo cost per solved taskModel BHy3 previewTencent22.4/1001 independent benchmarkNo cost per solved task
Shared results
34
Qwen3.5 397B A17B only
31
Hy3 preview only
2
Like-for-like categories
7 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
Qwen3.5 397B A17B 28.6 from 1 benchmark, Hy3 preview 22.4 from 1 benchmark.
Widest category
General, 8.0 points apart on average over 15 shared benchmarks.
Widest single gap
IFBench: Qwen3.5 397B A17B 78.8% against Hy3 preview 63.1%, 15.6 points apart on a 0 to 100 scale.
Output price
Qwen3.5 397B A17B $2.34 against Hy3 preview $0.60 per million output tokens, 3.9x apart.
Context window
Both take 262K 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
CategoryQwen3.5 397B A17BBarsHy3 previewTies
Coding60
Intelligence01
Agentic work10
Reasoning50
Math20
Knowledge40
General150
All shared boards331
CodingLike-for-likeFour of these boards feed the Vibe Coding Index60
Coding benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
LMArena WebDev14001357Qwen3.5 397B A17B
AA Coding IndexNot measured58.8Only Hy3 preview measured
SciCode44.8%Not measuredOnly Qwen3.5 397B A17B measured
Terminal-Bench Hard (Artificial Analysis run)40.9%34.1%Qwen3.5 397B A17B
ALE-Bench621.9Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: coding14641421Qwen3.5 397B A17B
LMArena Text: software and IT14631423Qwen3.5 397B A17B
LMArena WebDev: React13881349Qwen3.5 397B A17B
LMArena WebDev: HTML14101356Qwen3.5 397B A17B
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
AA Intelligence Index21.425.3Hy3 preview
Epoch Capabilities Index146.8Not measuredOnly Qwen3.5 397B A17B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom95.6%92.7%Qwen3.5 397B A17B
APEX-Agents24.9%Not measuredOnly Qwen3.5 397B A17B measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
GPQA Diamond (Artificial Analysis run)89.3%86.7%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)29.0%27.8%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)86.4%Not measuredOnly Qwen3.5 397B A17B measured
Mystery game puzzles18.0%Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: hard prompts14481413Qwen3.5 397B A17B
LMArena Text: expert14621422Qwen3.5 397B A17B
LMArena Text: hard prompts in English14501416Qwen3.5 397B A17B
LMArena Vision: diagrams1277Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: homework1292Not measuredOnly Qwen3.5 397B A17B measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
OTIS Mock AIME88.9%Not measuredOnly Qwen3.5 397B A17B measured
FrontierMath, tiers 1 to 331.2%Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: math14531424Qwen3.5 397B A17B
LMArena Text: mathematical work14541442Qwen3.5 397B A17B
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
LMArena Text: science14571416Qwen3.5 397B A17B
LMArena Text: medicine and healthcare14551405Qwen3.5 397B A17B
LMArena Text: legal and government14411430Qwen3.5 397B A17B
LMArena Text: business and finance14351397Qwen3.5 397B A17B
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
Design Arena: websites1191Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: UI components1163Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: game dev1141Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: data viz1175Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: 3D1161Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: all code categories1180Not measuredOnly Qwen3.5 397B A17B measured
Design Arena: SVG1139Not measuredOnly Qwen3.5 397B A17B measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
IFBench78.8%63.1%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)77.3%64.7%Qwen3.5 397B A17B
DTBench87.5%Not measuredOnly Qwen3.5 397B A17B measured
LMCA37.9%Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text14371401Qwen3.5 397B A17B
LMArena Text: instruction following14241383Qwen3.5 397B A17B
LMArena Text: creative writing14021339Qwen3.5 397B A17B
LMArena Vision1262Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: English14431409Qwen3.5 397B A17B
LMArena Text: non-English14301390Qwen3.5 397B A17B
LMArena Text: Chinese14981435Qwen3.5 397B A17B
LMArena Text: German1445Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: Japanese1429Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: Korean1384Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: French14621425Qwen3.5 397B A17B
LMArena Text: Spanish14411399Qwen3.5 397B A17B
LMArena Text: Russian14301399Qwen3.5 397B A17B
LMArena Text: Polish1447Not measuredOnly Qwen3.5 397B A17B measured
LMArena Text: multi-turn14461411Qwen3.5 397B A17B
LMArena Text: longer queries14411402Qwen3.5 397B A17B
LMArena Text: writing and language14151370Qwen3.5 397B A17B
LMArena Text: entertainment and media13991352Qwen3.5 397B A17B
LMArena Vision: English1268Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: Chinese1314Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: reading text1271Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: humor1262Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: captioning1230Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: recognizing things1265Not measuredOnly Qwen3.5 397B A17B measured
LMArena Vision: creative writing1260Not measuredOnly Qwen3.5 397B A17B measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3.5 397B A17B and Hy3 preview
BenchmarkQwen3.5 397B A17BHy3 previewLeader
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

Qwen3.5 397B A17B$0.0016Fits in one request
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

Qwen3.5 397B A17B$0.027Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

Qwen3.5 397B A17B$0.101Fits in one request
Hy3 preview$0.042Fits in one request

Hy3 preview 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 Qwen3.5 397B A17B and Hy3 preview
SpecificationQwen3.5 397B A17BTencent Hy3 preview
MakerQwenTencent
WeightsOpen weightsOpen weights
ReleasedFebruary 16, 2026April 22, 2026
Context window262K262K
Input $/Mtok$0.39$0.18
Output $/Mtok$2.34$0.60
Coding index28.622.4
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.5 397B A17B better than Hy3 preview for coding?

Pick Qwen3.5 397B A17B for coding: it scores 28.6 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when output tokens cost 3.9x less, or when the benchmark that matters is AA Intelligence Index, where it leads.

Which is cheaper, Qwen3.5 397B A17B or Hy3 preview?

Qwen3.5 397B A17B costs $0.39 per million input tokens and $2.34 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3.5 397B A17B or Hy3 preview?

Neither: both take 262K tokens.

How many benchmarks is the Qwen3.5 397B A17B vs Hy3 preview comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. Qwen3.5 397B A17B's coding index rests on 1 independent benchmark and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next