Step 3.5 Flash vs Hy3
Updated October 21, 2026. 31 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Step 3.5 Flash has the edge where output tokens cost 1.8x less, and where what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 31
- Step 3.5 Flash only
- 4
- Hy3 only
- 13
- Like-for-like categories
- 5 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Step 3.5 Flash has a AA Intelligence Index result, 17.0.
Directional only
Web design
Design Arena: websites
No call
Only Hy3 has a Design Arena: websites result, 1230.
Directional only
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 3.5 Flash
Step 3.5 Flash $0.0003, Hy3 $0.0004 per turn.
List prices
At a glance
- Coding index
- Step 3.5 Flash not benchmarked, Hy3 not benchmarked.
- Widest category
- Math, 10.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Step 3.5 Flash 63.0% against Hy3 79.0%, 16.0 points apart on a 0 to 100 scale.
- Output price
- Step 3.5 Flash $0.30 against Hy3 $0.528 per million output tokens, 1.8x 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.
| Category | Step 3.5 Flash | Bars | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 18 | ||
| All shared boards | 0 | 31 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1507 | Only Hy3 measured |
| SciCode | Not measured | 48.6% | Only Hy3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 32.6% | Not measured | Only Step 3.5 Flash measured |
| ALE-Bench | Not measured | 838.6 | Only Hy3 measured |
| LMArena Text: coding | 1436 | 1466 | Hy3 |
| LMArena Text: software and IT | 1434 | 1463 | Hy3 |
| LMArena WebDev: React | Not measured | 1511 | Only Hy3 measured |
| LMArena WebDev: HTML | Not measured | 1487 | Only Hy3 measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 17.0 | Not measured | Only Step 3.5 Flash measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 94.4% | Not measured | Only Step 3.5 Flash measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 83.1% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 24.5% | 33.5% | Hy3 |
| LMArena Text: hard prompts | 1411 | 1447 | Hy3 |
| LMArena Text: expert | 1421 | 1461 | Hy3 |
| LMArena Text: hard prompts in English | 1421 | 1455 | Hy3 |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| LMArena Text: math | 1408 | 1473 | Hy3 |
| LMArena Text: mathematical work | 1421 | 1482 | Hy3 |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| LMArena Text: science | 1415 | 1457 | Hy3 |
| LMArena Text: medicine and healthcare | 1408 | 1452 | Hy3 |
| LMArena Text: legal and government | 1408 | 1422 | Hy3 |
| LMArena Text: business and finance | 1394 | 1424 | Hy3 |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1230 | Only Hy3 measured |
| Design Arena: UI components | Not measured | 1207 | Only Hy3 measured |
| Design Arena: game dev | Not measured | 1208 | Only Hy3 measured |
| Design Arena: data viz | Not measured | 1163 | Only Hy3 measured |
| Design Arena: 3D | Not measured | 1233 | Only Hy3 measured |
| Design Arena: all code categories | Not measured | 1227 | Only Hy3 measured |
| Design Arena: SVG | Not measured | 1200 | Only Hy3 measured |
| Design Arena: ASCII art | Not measured | 1157 | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
| Benchmark | Step 3.5 Flash | Hy3 | Leader |
|---|---|---|---|
| IFBench | 66.5% | Not measured | Only Step 3.5 Flash measured |
| Long context reasoning (AA-LCR) | 63.0% | 79.0% | Hy3 |
| LMArena Text | 1403 | 1438 | Hy3 |
| LMArena Text: instruction following | 1385 | 1426 | Hy3 |
| LMArena Text: creative writing | 1357 | 1403 | Hy3 |
| LMArena Text: English | 1417 | 1448 | Hy3 |
| LMArena Text: non-English | 1385 | 1426 | Hy3 |
| LMArena Text: Chinese | 1446 | 1485 | Hy3 |
| LMArena Text: German | 1405 | 1449 | Hy3 |
| LMArena Text: Japanese | 1353 | 1397 | Hy3 |
| LMArena Text: Korean | 1351 | 1396 | Hy3 |
| LMArena Text: French | 1421 | 1456 | Hy3 |
| LMArena Text: Spanish | 1419 | 1457 | Hy3 |
| LMArena Text: Russian | 1385 | 1432 | Hy3 |
| LMArena Text: Polish | 1389 | 1447 | Hy3 |
| LMArena Text: multi-turn | 1404 | 1436 | Hy3 |
| LMArena Text: longer queries | 1402 | 1442 | Hy3 |
| LMArena Text: writing and language | 1372 | 1414 | Hy3 |
| LMArena Text: entertainment and media | 1360 | 1400 | Hy3 |
| 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
| Benchmark | Step 3.5 Flash | Hy3 | 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
Step 3.5 Flash costs less
Repository review
50K input + 3K output tokens
Step 3.5 Flash costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | StepFun Step 3.5 Flash | Tencent Hy3 |
|---|---|---|
| Maker | StepFun | Tencent |
| Weights | Open weights | Open weights |
| Released | January 29, 2026 | July 6, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.10 | $0.132 |
| Output $/Mtok | $0.30 | $0.528 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Step 3.5 Flash better than Hy3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Step 3.5 Flash has the edge where output tokens cost 1.8x less, and where what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Step 3.5 Flash or Hy3?
Step 3.5 Flash costs $0.10 per million input tokens and $0.30 per million output tokens; Hy3 costs $0.132 and $0.528. Cost per solved task is known for neither of them.
Which has the bigger context window, Step 3.5 Flash or Hy3?
Neither: both take 262K tokens.
How many benchmarks is the Step 3.5 Flash vs Hy3 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's on 1. Where only one model has a result, the page says so instead of naming a winner.