Enter opens the highlighted result. Esc closes.

Step 3.5 Flash vs Hy3 preview

Hy3 preview leads Step 3.5 Flash on the Artificial Analysis Intelligence Index, 25.3 to 17.0, and Step 3.5 Flash costs 2.0x less per output token ($0.30 vs $0.60 per million). Updated October 21, 2026; 31 benchmarks have a result for both.

Replace Step 3.5 Flash Replace Hy3 preview
Step 3.5 FlashStepFun
Coding
No data
Overall
17.0
Output $/M
$0.30
15
Hy3 previewTencent
Coding
No data
Overall
25.3
Output $/M
$0.60
16
vs boards won of 31 shared

Step 3.5 Flash or Hy3 preview: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Step 3.5 Flash for output tokens 2.0x cheaper ($0.30 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.

Model AStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved taskModel BHy3 previewTencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
31
Step 3.5 Flash only
4
Hy3 preview only
5
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
Step 3.5 Flash not benchmarked, Hy3 preview not benchmarked.
Widest category
Intelligence, 8.3 points apart on average over 1 shared benchmark.
Widest single gap
AA Intelligence Index: Step 3.5 Flash 17.0 against Hy3 preview 25.3, 8.3 points apart on a 0 to 100 scale.
Output price
Step 3.5 Flash $0.30 against Hy3 preview $0.60 per million output tokens, 2.0x 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
CategoryStep 3.5 FlashBarsHy3 previewTies
Coding21
Intelligence01
Agentic work10
Reasoning14
Math02
Knowledge13
General105
All shared boards1516
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
Coding benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
LMArena WebDevNot measured1357Only Hy3 preview measured
AA Coding IndexNot measured58.8Only Hy3 preview measured
Terminal-Bench Hard (Artificial Analysis run)32.6%34.1%Hy3 preview
LMArena Text: coding14361421Step 3.5 Flash
LMArena Text: software and IT14341423Step 3.5 Flash
LMArena WebDev: ReactNot measured1349Only Hy3 preview measured
LMArena WebDev: HTMLNot measured1356Only Hy3 preview measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
AA Intelligence Index17.025.3Hy3 preview
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom94.4%92.7%Step 3.5 Flash
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
GPQA Diamond (Artificial Analysis run)83.1%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)24.5%27.8%Hy3 preview
LMArena Text: hard prompts14111413Hy3 preview
LMArena Text: expert14211422Hy3 preview
LMArena Text: hard prompts in English14211416Step 3.5 Flash
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
LMArena Text: math14081424Hy3 preview
LMArena Text: mathematical work14211442Hy3 preview
Neither model has a result on the other 11 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
Knowledge benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
LMArena Text: science14151416Hy3 preview
LMArena Text: medicine and healthcare14081405Step 3.5 Flash
LMArena Text: legal and government14081430Hy3 preview
LMArena Text: business and finance13941397Hy3 preview
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index105
General benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 previewLeader
IFBench66.5%63.1%Step 3.5 Flash
Long context reasoning (AA-LCR)63.0%64.7%Hy3 preview
LMArena Text14031401Step 3.5 Flash
LMArena Text: instruction following13851383Step 3.5 Flash
LMArena Text: creative writing13571339Step 3.5 Flash
LMArena Text: English14171409Step 3.5 Flash
LMArena Text: non-English13851390Hy3 preview
LMArena Text: Chinese14461435Step 3.5 Flash
LMArena Text: German1405Not measuredOnly Step 3.5 Flash measured
LMArena Text: Japanese1353Not measuredOnly Step 3.5 Flash measured
LMArena Text: Korean1351Not measuredOnly Step 3.5 Flash measured
LMArena Text: French14211425Hy3 preview
LMArena Text: Spanish14191399Step 3.5 Flash
LMArena Text: Russian13851399Hy3 preview
LMArena Text: Polish1389Not measuredOnly Step 3.5 Flash measured
LMArena Text: multi-turn14041411Hy3 preview
LMArena Text: longer queries14021402Step 3.5 Flash
LMArena Text: writing and language13721370Step 3.5 Flash
LMArena Text: entertainment and media13601352Step 3.5 Flash
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Step 3.5 Flash and Hy3 preview
BenchmarkStep 3.5 FlashHy3 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

Step 3.5 Flash$0.0003Fits in one request
Hy3 preview$0.0005Fits in one request

Step 3.5 Flash costs less

Repository review

50K input + 3K output tokens

Step 3.5 Flash$0.0059Fits in one request
Hy3 preview$0.011Fits in one request

Step 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

Step 3.5 Flash$0.023Fits in one request
Hy3 preview$0.042Fits in one request

Step 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 Step 3.5 Flash and Hy3 preview
SpecificationStepFun Step 3.5 FlashTencent Hy3 preview
MakerStepFunTencent
WeightsOpen weightsOpen weights
ReleasedJanuary 29, 2026April 22, 2026
Context window262K262K
Input $/Mtok$0.10$0.18
Output $/Mtok$0.30$0.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Step 3.5 Flash better than Hy3 preview for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Step 3.5 Flash for output tokens 2.0x cheaper ($0.30 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.

Which is cheaper, Step 3.5 Flash or Hy3 preview?

Step 3.5 Flash costs $0.10 per million input tokens and $0.30 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, Step 3.5 Flash or Hy3 preview?

Neither: both take 262K tokens.

How many benchmarks is the Step 3.5 Flash vs Hy3 preview comparison based on?

31 benchmarks have a result for both models as of October 21, 2026. Step 3.5 Flash's coding index rests on 0 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