Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Hy3 preview

Hy3 preview leads DeepSeek V3.2 on the Artificial Analysis Intelligence Index, 25.3 to 21.5, and Hy3 preview costs 1.5x less per output token ($0.60 vs $0.88 per million). Updated October 22, 2026; 35 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Hy3 preview
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
27
Hy3 previewTencent
Coding
No data
Overall
No data
Output $/M
$0.60
8
vs boards won of 35 shared

DeepSeek V3.2 or Hy3 preview: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding.

Pick Hy3 preview for output tokens 1.5x cheaper ($0.60 vs $0.88 per million) and a larger context window (262K against 164K tokens).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BHy3 previewTencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
35
DeepSeek V3.2 only
40
Hy3 preview only
1
Like-for-like categories
7 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
DeepSeek V3.2 30.0 from 3 benchmarks, Hy3 preview not benchmarked.
Widest category
General, 4.7 points apart on average over 15 shared benchmarks.
Widest single gap
AA Coding Index: DeepSeek V3.2 44.2 against Hy3 preview 58.8, 14.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Hy3 preview $0.60 per million output tokens, 1.5x apart.
Context window
DeepSeek V3.2 takes 164K tokens, Hy3 preview 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
CategoryDeepSeek V3.2BarsHy3 previewTies
Coding61
Intelligence01
Agentic work01
Reasoning32
Math11
Knowledge31
General141
All shared boards278
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
Coding benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621357DeepSeek V3.2
AA Coding Index44.258.8Hy3 preview
LiveCodeBench (Vals AI)80.7%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%34.1%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: coding14531421DeepSeek V3.2
LMArena Text: software and IT14491423DeepSeek V3.2
LMArena WebDev: React13501349DeepSeek V3.2
LMArena WebDev: HTML13711356DeepSeek V3.2
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
AA Intelligence Index21.525.3Hy3 preview
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V3.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom90.6%92.7%Hy3 preview
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
Reasoning benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)24.6%27.8%Hy3 preview
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341413DeepSeek V3.2
LMArena Text: expert14361422DeepSeek V3.2
LMArena Text: hard prompts in English14461416DeepSeek V3.2
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index11
Math benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.0Not measuredOnly DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)92.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: math14351424DeepSeek V3.2
LMArena Text: mathematical work14401442Hy3 preview
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
Knowledge benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
MMLU Pro84.9%Not measuredOnly DeepSeek V3.2 measured
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%Not measuredOnly DeepSeek V3.2 measured
TaxEval (Vals AI)68.2%Not measuredOnly DeepSeek V3.2 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: science14461416DeepSeek V3.2
LMArena Text: medicine and healthcare14401405DeepSeek V3.2
LMArena Text: legal and government14251430Hy3 preview
LMArena Text: business and finance14101397DeepSeek V3.2
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
Design Arena: websites1175Not measuredOnly DeepSeek V3.2 measured
Design Arena: UI components1146Not measuredOnly DeepSeek V3.2 measured
Design Arena: game dev1131Not measuredOnly DeepSeek V3.2 measured
Design Arena: data viz1158Not measuredOnly DeepSeek V3.2 measured
Design Arena: 3D1132Not measuredOnly DeepSeek V3.2 measured
Design Arena: all code categories1163Not measuredOnly DeepSeek V3.2 measured
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1083Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index141
General benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 previewLeader
IFBench60.7%63.1%Hy3 preview
Long context reasoning (AA-LCR)73.3%64.7%DeepSeek V3.2
DTBench85.6%Not measuredOnly DeepSeek V3.2 measured
LMCA28.8%Not measuredOnly DeepSeek V3.2 measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251401DeepSeek V3.2
LMArena Text: instruction following14131383DeepSeek V3.2
LMArena Text: creative writing14001339DeepSeek V3.2
LMArena Text: English14391409DeepSeek V3.2
LMArena Text: non-English14091390DeepSeek V3.2
LMArena Text: Chinese14551435DeepSeek V3.2
LMArena Text: German1413Not measuredOnly DeepSeek V3.2 measured
LMArena Text: Japanese1374Not measuredOnly DeepSeek V3.2 measured
LMArena Text: Korean1370Not measuredOnly DeepSeek V3.2 measured
LMArena Text: French14291425DeepSeek V3.2
LMArena Text: Spanish14241399DeepSeek V3.2
LMArena Text: Russian14241399DeepSeek V3.2
LMArena Text: Polish1419Not measuredOnly DeepSeek V3.2 measured
LMArena Text: multi-turn14271411DeepSeek V3.2
LMArena Text: longer queries14281402DeepSeek V3.2
LMArena Text: writing and language14071370DeepSeek V3.2
LMArena Text: entertainment and media13951352DeepSeek V3.2
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and Hy3 preview
BenchmarkDeepSeek V3.2Hy3 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

DeepSeek V3.2$0.0007Fits in one request
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
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 DeepSeek V3.2 and Hy3 preview
SpecificationDeepSeek V3.2Tencent Hy3 preview
MakerDeepSeekTencent
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025April 22, 2026
Context window164K262K
Input $/Mtok$0.29$0.18
Output $/Mtok$0.88$0.60
Coding index30.0Not benchmarked
Independent measurements behind it31
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Hy3 preview for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding. Pick Hy3 preview for output tokens 1.5x cheaper ($0.60 vs $0.88 per million) and a larger context window (262K against 164K tokens).

Which is cheaper, DeepSeek V3.2 or Hy3 preview?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3.2 or Hy3 preview?

Hy3 preview, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs Hy3 preview comparison based on?

35 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next