Step 5 Preview 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
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 43.9 for Hy3.
Pick Hy3 when output tokens cost 5.1x less, or when what matters is LMArena Text: hard prompts in English or LMArena Text: math, where it leads.
- Shared results
- 31
- Step 5 Preview only
- 30
- 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, four public coding benchmarks
Step 5 Preview
Step 5 Preview scores 71.4 against 43.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Step 5 Preview has a AA Intelligence Index result, 43.7.
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
Step 5 Preview
Step 5 Preview takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
Step 5 Preview $0.0024, Hy3 $0.0004 per turn.
List prices
At a glance
- Coding index
- Step 5 Preview 71.4 from 2 benchmarks, Hy3 43.9 from 1 benchmark.
- Widest category
- Coding, 7.9 points apart on average over 6 shared benchmarks.
- Widest single gap
- Humanity's Last Exam (Artificial Analysis run): Step 5 Preview 46.5% against Hy3 33.5%, 13.0 points apart on a 0 to 100 scale.
- Output price
- Step 5 Preview $2.70 against Hy3 $0.528 per million output tokens, 5.1x apart.
- Context window
- Step 5 Preview takes 1.05M tokens, Hy3 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.
| Category | Step 5 Preview | Bars | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Reasoning | 3 | 1 | ||
| Math | 0 | 2 | ||
| Knowledge | 2 | 2 | ||
| General | 11 | 4 | ||
| All shared boards | 22 | 9 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index60
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| LiveBench coding | 85.6% | Not measured | Only Step 5 Preview measured |
| LMArena WebDev | 1567 | 1507 | Step 5 Preview |
| Terminal-Bench 4 (Vals AI) | 31.8% | Not measured | Only Step 5 Preview measured |
| Vibe Code Bench (Vals AI) | 70.4% | Not measured | Only Step 5 Preview measured |
| Code migration (Vals AI) | 39.0% | Not measured | Only Step 5 Preview measured |
| IOI (Vals AI) | 38.1% | Not measured | Only Step 5 Preview measured |
| SWE-bench Multimodal (Vals AI) | 40.8% | Not measured | Only Step 5 Preview measured |
| SciCode | 58.9% | 48.6% | Step 5 Preview |
| ALE-Bench | Not measured | 838.6 | Only Hy3 measured |
| LMArena Text: coding | 1485 | 1466 | Step 5 Preview |
| LMArena Text: software and IT | 1473 | 1463 | Step 5 Preview |
| LMArena WebDev: React | 1583 | 1511 | Step 5 Preview |
| LMArena WebDev: HTML | 1556 | 1487 | Step 5 Preview |
| LMArena WebDev: from an image | 1550 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.7 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| LiveBench research | 72.8% | Not measured | Only Step 5 Preview measured |
| LiveBench browser | 24.0% | Not measured | Only Step 5 Preview measured |
| LiveBench long agentic | 27.5% | Not measured | Only Step 5 Preview measured |
| SREBench (Vals AI) | 0.4% | Not measured | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | 50.7% | Not measured | Only Step 5 Preview measured |
| Tax Agent Bench (Vals AI) | 27.3% | Not measured | Only Step 5 Preview measured |
| Legal Research Bench (Vals AI) | 40.4% | Not measured | Only Step 5 Preview measured |
| Excel Modeling Benchmark (Vals AI) | 57.1% | Not measured | Only Step 5 Preview measured |
| BioMysteryBench (Vals AI) | 67.4% | Not measured | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | 2.9% | Not measured | Only Step 5 Preview measured |
| Vals Science Index | 29.6% | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| LiveBench reasoning | 83.8% | Not measured | Only Step 5 Preview measured |
| MysteryMechanism (Vals AI) | 18.5% | Not measured | Only Step 5 Preview measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.7% | Only Hy3 measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.5% | 33.5% | Step 5 Preview |
| LMArena Text: hard prompts | 1461 | 1447 | Step 5 Preview |
| LMArena Text: expert | 1485 | 1461 | Step 5 Preview |
| LMArena Text: hard prompts in English | 1454 | 1455 | Hy3 |
| LMArena Vision: diagrams | 1308 | Not measured | Only Step 5 Preview measured |
| LMArena Vision: homework | 1265 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| ProofBench | 42.0% | Not measured | Only Step 5 Preview measured |
| LMArena Text: math | 1458 | 1473 | Hy3 |
| LMArena Text: mathematical work | 1460 | 1482 | Hy3 |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| LMArena Text: science | 1454 | 1457 | Hy3 |
| LMArena Text: medicine and healthcare | 1439 | 1452 | Hy3 |
| LMArena Text: legal and government | 1437 | 1422 | Step 5 Preview |
| LMArena Text: business and finance | 1435 | 1424 | Step 5 Preview |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1230 | Only Hy3 measured |
| Design Arena: UI components | Not measured | 1205 | 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 | 1199 | Only Hy3 measured |
| Design Arena: ASCII art | Not measured | 1157 | Only Hy3 measured |
| LiveBench design | 76.9% | Not measured | Only Step 5 Preview measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index114
| Benchmark | Step 5 Preview | Hy3 | Leader |
|---|---|---|---|
| LiveBench data analysis | 63.5% | Not measured | Only Step 5 Preview measured |
| Public Benefits Bench (Vals AI) | 58.1% | Not measured | Only Step 5 Preview measured |
| Long context reasoning (AA-LCR) | 88.3% | 79.0% | Step 5 Preview |
| LMArena Text | 1440 | 1438 | Step 5 Preview |
| LMArena Text: instruction following | 1438 | 1426 | Step 5 Preview |
| LMArena Text: creative writing | 1409 | 1403 | Step 5 Preview |
| LMArena Vision | 1265 | Not measured | Only Step 5 Preview measured |
| LMArena Text: English | 1447 | 1448 | Hy3 |
| LMArena Text: non-English | 1428 | 1426 | Step 5 Preview |
| LMArena Text: Chinese | 1500 | 1485 | Step 5 Preview |
| LMArena Text: German | Not measured | 1449 | Only Hy3 measured |
| LMArena Text: Japanese | 1383 | 1397 | Hy3 |
| LMArena Text: Korean | Not measured | 1396 | Only Hy3 measured |
| LMArena Text: French | 1438 | 1456 | Hy3 |
| LMArena Text: Spanish | 1441 | 1457 | Hy3 |
| LMArena Text: Russian | 1433 | 1432 | Step 5 Preview |
| LMArena Text: Polish | Not measured | 1447 | Only Hy3 measured |
| LMArena Text: multi-turn | 1437 | 1436 | Step 5 Preview |
| LMArena Text: longer queries | 1449 | 1442 | Step 5 Preview |
| LMArena Text: writing and language | 1425 | 1414 | Step 5 Preview |
| LMArena Text: entertainment and media | 1412 | 1400 | Step 5 Preview |
| LMArena Vision: English | 1290 | Not measured | Only Step 5 Preview measured |
| LMArena Vision: reading text | 1282 | Not measured | Only Step 5 Preview measured |
| 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
| Benchmark | Step 5 Preview | 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
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 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 5 Preview | Tencent Hy3 |
|---|---|---|
| Maker | StepFun | Tencent |
| Weights | Open weights | Open weights |
| Released | October 8, 2026 | July 6, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $1.00 | $0.132 |
| Output $/Mtok | $2.70 | $0.528 |
| Coding index | 71.4 | 43.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Step 5 Preview better than Hy3 for coding?
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 43.9 for Hy3. Pick Hy3 when output tokens cost 5.1x less, or when what matters is LMArena Text: hard prompts in English or LMArena Text: math, where it leads.
Which is cheaper, Step 5 Preview or Hy3?
Step 5 Preview costs $1.00 per million input tokens and $2.70 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 5 Preview or Hy3?
Step 5 Preview, with 1.05M tokens against 262K.
How many benchmarks is the Step 5 Preview vs Hy3 comparison based on?
31 benchmarks have a result for both models as of October 21, 2026. Step 5 Preview's coding index rests on 2 independent benchmarks and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.