Hy4 preview vs Inkling
Hy4 preview leads Inkling on coding, 44.3 to 31.5 on the Vibe Coding Index, and Hy4 preview costs 1.8x less per output token ($2.2509 vs $4.05 per million). Updated October 21, 2026; 22 benchmarks have a result for both.
Hy4 preview or Inkling: which to pick
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6.
Pick Inkling for work measured by CyberBench (Vals AI) or MedScribe (Vals AI), where it leads.
- Shared results
- 22
- Hy4 preview only
- 2
- Inkling only
- 80
- Like-for-like categories
- 5 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.
Coding
Vibe Coding Index, six public coding benchmarks
Hy4 preview
Hy4 preview scores 44.3 against 31.5.
3 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Inkling has a AA Intelligence Index result, 25.0.
Directional only
Agentic work
AA Agentic Index
No call
Only Inkling has a AA Agentic Index result, 22.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling has a GPQA Diamond result, 87.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling has a MMLU Pro result, 86.3%.
Directional only
Web design
Design Arena: websites
No call
Only Inkling has a Design Arena: websites result, 1224.
Directional only
General
Vals Index
Hy4 preview
Hy4 preview leads, 53.2% against 29.0%.
Same board, both measured
Long documents
Listed context window
Hy4 preview
Hy4 preview takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4 preview
Hy4 preview $0.0019, Inkling $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling has the number, $0.76.
Directional only
At a glance
- Coding index
- Hy4 preview 44.3 from 3 benchmarks, Inkling 31.5 from 6 benchmarks.
- Widest category
- Math, 75.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ProofBench: Hy4 preview 75.0% against Inkling 0.0%, 75.0 points apart on a 0 to 100 scale.
- Output price
- Hy4 preview $2.2509 against Inkling $4.05 per million output tokens, 1.8x apart.
- Context window
- Hy4 preview takes 1.05M tokens, Inkling 524K.
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 | Hy4 preview | Bars | Inkling | Ties |
|---|---|---|---|---|
| Coding | 8 | 1 | 1 tie | |
| Agentic work | 6 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 2 | 0 | ||
| General | 2 | 1 | ||
| All shared boards | 19 | 2 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index81
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 64.0% | Only Inkling measured |
| LMArena WebDev | 1631 | 1414 | Hy4 preview |
| AA Coding Index | Not measured | 52.1 | Only Inkling measured |
| LiveCodeBench (Vals AI) | Not measured | 85.5% | Only Inkling measured |
| SWE-bench Verified (Vals AI) | Not measured | 77.6% | Only Inkling measured |
| Terminal-Bench 4 (Vals AI) | 8.1% | 0.5% | Hy4 preview |
| Vibe Code Bench (Vals AI) | 77.5% | 19.2% | Hy4 preview |
| Code migration (Vals AI) | 47.4% | 11.8% | Hy4 preview |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | 59.3% | 14.9% | Hy4 preview |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | 47.6% | Hy4 preview |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 7.3% | Only Inkling measured |
| SkillsBench (Vals AI) | Not measured | 26.1% | Only Inkling measured |
| CyberBench (Vals AI) | 65.4% | 66.8% | Inkling |
| SciCode | Not measured | 47.0% | Only Inkling measured |
| FrontierCode | Not measured | 14.0% | Only Inkling measured |
| FrontierSWE | Not measured | 4.1% | Only Inkling measured |
| WeirdML | Not measured | 32.3% | Only Inkling measured |
| ALE-Bench | Not measured | 946.0 | Only Inkling measured |
| LMArena Text: coding | Not measured | 1466 | Only Inkling measured |
| LMArena Text: software and IT | Not measured | 1465 | Only Inkling measured |
| LMArena WebDev: React | 1653 | 1404 | Hy4 preview |
| LMArena WebDev: HTML | 1620 | 1399 | Hy4 preview |
| Neither model has a result on the other 16 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 25.0 | Only Inkling measured |
| Epoch Capabilities Index | Not measured | 148.4 | Only Inkling measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 22.5 | Only Inkling measured |
| Design Arena: agents building web apps | Not measured | 1196 | Only Inkling measured |
| LiveBench research | Not measured | 59.9% | Only Inkling measured |
| LiveBench browser | Not measured | 16.0% | Only Inkling measured |
| LiveBench long agentic | Not measured | 14.1% | Only Inkling measured |
| SREBench (Vals AI) | 2.3% | 0.0% | Hy4 preview |
| Finance Agent (Vals AI) | 55.1% | 46.6% | Hy4 preview |
| Tax Agent Bench (Vals AI) | 32.6% | 15.3% | Hy4 preview |
| Legal Research Bench (Vals AI) | 45.2% | 28.4% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 8.8% | 3.8% | Hy4 preview |
| Excel Modeling Benchmark (Vals AI) | 58.1% | 38.4% | Hy4 preview |
| BioMysteryBench (Vals AI) | 69.3% | Not measured | Only Hy4 preview measured |
| Terminal-Bench-Science (Vals AI) | 1.4% | Not measured | Only Hy4 preview measured |
| APEX-Agents | Not measured | 33.8% | Only Inkling measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 87.1% | Only Inkling measured |
| LiveBench reasoning | Not measured | 78.3% | Only Inkling measured |
| MMMU Pro (Vals AI) | Not measured | 78.5% | Only Inkling measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 87.2% | Only Inkling measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 31.9% | Only Inkling measured |
| GPQA Diamond (Epoch AI run) | Not measured | 88.3% | Only Inkling measured |
| ARC-AGI | Not measured | 79.5% | Only Inkling measured |
| ARC-AGI-2 | Not measured | 36.5% | Only Inkling measured |
| SimpleBench | Not measured | 50.0% | Only Inkling measured |
| Chess puzzles | Not measured | 21.0% | Only Inkling measured |
| LMArena Text: hard prompts | Not measured | 1451 | Only Inkling measured |
| LMArena Text: expert | Not measured | 1466 | Only Inkling measured |
| LMArena Text: hard prompts in English | Not measured | 1448 | Only Inkling measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 88.9% | Only Inkling measured |
| FrontierMath, tiers 1 to 3 | Not measured | 33.3% | Only Inkling measured |
| FrontierMath, tier 4 | Not measured | 4.9% | Only Inkling measured |
| ProofBench | 75.0% | 0.0% | Hy4 preview |
| LMArena Text: math | Not measured | 1479 | Only Inkling measured |
| LMArena Text: mathematical work | Not measured | 1460 | Only Inkling measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.3% | Only Inkling measured |
| LegalBench (Vals AI) | 83.8% | 83.0% | Hy4 preview |
| CorpFin (Vals AI) | Not measured | 68.6% | Only Inkling measured |
| TaxEval (Vals AI) | Not measured | 75.3% | Only Inkling measured |
| MortgageTax (Vals AI) | Not measured | 64.0% | Only Inkling measured |
| MedCode (Vals AI) | 43.3% | 41.2% | Hy4 preview |
| SimpleQA Verified | Not measured | 40.3% | Only Inkling measured |
| LMArena Text: science | Not measured | 1455 | Only Inkling measured |
| LMArena Text: medicine and healthcare | Not measured | 1447 | Only Inkling measured |
| LMArena Text: legal and government | Not measured | 1448 | Only Inkling measured |
| LMArena Text: business and finance | Not measured | 1438 | Only Inkling measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1224 | Only Inkling measured |
| Design Arena: UI components | Not measured | 1201 | Only Inkling measured |
| Design Arena: game dev | Not measured | 1166 | Only Inkling measured |
| Design Arena: data viz | Not measured | 1159 | Only Inkling measured |
| Design Arena: 3D | Not measured | 1161 | Only Inkling measured |
| Design Arena: all code categories | Not measured | 1206 | Only Inkling measured |
| Design Arena: SVG | Not measured | 1110 | Only Inkling measured |
| Design Arena: ASCII art | Not measured | 1089 | Only Inkling measured |
| LiveBench design | Not measured | 58.3% | Only Inkling measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Hy4 preview | Inkling | Leader |
|---|---|---|---|
| Vals Index | 53.2% | 29.0% | Hy4 preview |
| LiveBench data analysis | Not measured | 72.8% | Only Inkling measured |
| Public Benefits Bench (Vals AI) | 68.6% | 58.5% | Hy4 preview |
| SAGE (Vals AI) | Not measured | 36.5% | Only Inkling measured |
| MedScribe (Vals AI) | 83.6% | 85.4% | Inkling |
| Vals Multimodal Index | Not measured | 49.4% | Only Inkling measured |
| Long context reasoning (AA-LCR) | Not measured | 77.3% | Only Inkling measured |
| DTBench | Not measured | 87.5% | Only Inkling measured |
| LMCA | Not measured | 37.6% | Only Inkling measured |
| LMArena Text | Not measured | 1442 | Only Inkling measured |
| LMArena Text: instruction following | Not measured | 1425 | Only Inkling measured |
| LMArena Text: creative writing | Not measured | 1390 | Only Inkling measured |
| LMArena Text: English | Not measured | 1442 | Only Inkling measured |
| LMArena Text: non-English | Not measured | 1434 | Only Inkling measured |
| LMArena Text: Chinese | Not measured | 1493 | Only Inkling measured |
| LMArena Text: German | Not measured | 1445 | Only Inkling measured |
| LMArena Text: Japanese | Not measured | 1429 | Only Inkling measured |
| LMArena Text: Korean | Not measured | 1403 | Only Inkling measured |
| LMArena Text: French | Not measured | 1455 | Only Inkling measured |
| LMArena Text: Spanish | Not measured | 1449 | Only Inkling measured |
| LMArena Text: Russian | Not measured | 1430 | Only Inkling measured |
| LMArena Text: Polish | Not measured | 1450 | Only Inkling measured |
| LMArena Text: multi-turn | Not measured | 1437 | Only Inkling measured |
| LMArena Text: longer queries | Not measured | 1435 | Only Inkling measured |
| LMArena Text: writing and language | Not measured | 1404 | Only Inkling measured |
| LMArena Text: entertainment and media | Not measured | 1394 | Only Inkling measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | Inkling | 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
Hy4 preview costs less
Repository review
50K input + 3K output tokens
Hy4 preview costs less
Agent loop
200K input + 10K output tokens
Hy4 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.
| Specification | Tencent Hy4 preview | Thinking Machines Inkling |
|---|---|---|
| Maker | Tencent | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | August 28, 2026 | July 17, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.7506 | $0.975 |
| Output $/Mtok | $2.2509 | $4.05 |
| Coding index | 44.3 | 31.5 |
| Independent measurements behind it | 3 | 6 |
| Cost per solved task | Not computable | $0.76 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 preview better than Inkling for coding?
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6. Pick Inkling for work measured by CyberBench (Vals AI) or MedScribe (Vals AI), where it leads.
Which is cheaper, Hy4 preview or Inkling?
Hy4 preview costs $0.7506 per million input tokens and $2.2509 per million output tokens; Inkling costs $0.975 and $4.05. Cost per solved task is known for Inkling only.
Which has the bigger context window, Hy4 preview or Inkling?
Hy4 preview, with 1.05M tokens against 524K.
How many benchmarks is the Hy4 preview vs Inkling comparison based on?
22 benchmarks have a result for both models as of October 21, 2026. Hy4 preview's coding index rests on 3 independent benchmarks and Inkling's on 6. Where only one model has a result, the page says so instead of naming a winner.