Hy4 preview vs Inkling Small
Hy4 preview leads Inkling Small on coding, 44.3 to 27.3 on the Vibe Coding Index, and Inkling Small costs 2.1x less per output token ($1.20 vs $2.501 per million). Updated October 22, 2026; 21 benchmarks have a result for both.
Hy4 preview or Inkling Small: which to pick
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4.
Pick Inkling Small for output tokens 2.1x cheaper ($1.20 vs $2.501 per million) and work measured by ProgramBench (Vals AI) or MedScribe (Vals AI), where it leads.
- Shared results
- 21
- Hy4 preview only
- 3
- Inkling Small only
- 63
- 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 27.3.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Inkling Small has a AA Intelligence Index result, 25.7.
Directional only
Agentic work
AA Agentic Index
No call
Only Inkling Small has a AA Agentic Index result, 23.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling Small has a GPQA Diamond result, 83.6%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling Small has a MMLU Pro result, 85.6%.
Directional only
General
Vals Index
Hy4 preview
Hy4 preview leads, 53.2% against 27.6%.
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
Inkling Small
Hy4 preview $0.0021, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling Small has the number, $0.16.
Directional only
At a glance
- Coding index
- Hy4 preview 44.3 from 3 benchmarks, Inkling Small 27.3 from 4 benchmarks.
- Widest category
- Math, 69.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ProofBench: Hy4 preview 75.0% against Inkling Small 6.0%, 69.0 points apart on a 0 to 100 scale.
- Output price
- Hy4 preview $2.501 against Inkling Small $1.20 per million output tokens, 2.1x apart.
- Context window
- Hy4 preview takes 1.05M tokens, Inkling Small 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 Small | Ties |
|---|---|---|---|---|
| Coding | 8 | 1 | 1 tie | |
| Agentic work | 5 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 2 | 0 | ||
| General | 2 | 1 | ||
| All shared boards | 18 | 2 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index81
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| LMArena WebDev | 1631 | 1409 | Hy4 preview |
| AA Coding Index | Not measured | 52.9 | Only Inkling Small measured |
| LiveCodeBench (Vals AI) | Not measured | 85.9% | Only Inkling Small measured |
| SWE-bench Verified (Vals AI) | Not measured | 82.2% | Only Inkling Small measured |
| Terminal-Bench 4 (Vals AI) | 8.1% | 0.0% | Hy4 preview |
| Vibe Code Bench (Vals AI) | 77.5% | 19.1% | Hy4 preview |
| Code migration (Vals AI) | 47.4% | 13.7% | Hy4 preview |
| ProgramBench (Vals AI) | 0.0% | 0.5% | Inkling Small |
| IOI (Vals AI) | 59.3% | 9.3% | Hy4 preview |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | 55.1% | Tie |
| SkillsBench (Vals AI) | Not measured | 33.6% | Only Inkling Small measured |
| CyberBench (Vals AI) | 65.4% | 64.1% | Hy4 preview |
| SciCode | Not measured | 49.7% | Only Inkling Small measured |
| LMArena Text: coding | Not measured | 1450 | Only Inkling Small measured |
| LMArena Text: software and IT | Not measured | 1447 | Only Inkling Small measured |
| LMArena WebDev: React | 1653 | 1399 | Hy4 preview |
| LMArena WebDev: HTML | 1620 | 1398 | Hy4 preview |
| LMArena WebDev: from an image | Not measured | 1410 | Only Inkling Small measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 25.7 | Only Inkling Small measured |
| Epoch Capabilities Index | Not measured | 150.3 | Only Inkling Small measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 23.5 | Only Inkling Small measured |
| SREBench (Vals AI) | 2.3% | Not measured | Only Hy4 preview measured |
| Finance Agent (Vals AI) | 55.1% | 41.3% | Hy4 preview |
| Tax Agent Bench (Vals AI) | 32.6% | 15.4% | Hy4 preview |
| Legal Research Bench (Vals AI) | 45.2% | 25.5% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 8.8% | 2.9% | Hy4 preview |
| Excel Modeling Benchmark (Vals AI) | 58.1% | 31.8% | 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 |
| Neither model has a result on the other 32 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.6% | Only Inkling Small measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.5% | Only Inkling Small measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 33.3% | Only Inkling Small measured |
| GPQA Diamond (Epoch AI run) | Not measured | 88.5% | Only Inkling Small measured |
| ARC-AGI | Not measured | 84.0% | Only Inkling Small measured |
| ARC-AGI-2 | Not measured | 40.1% | Only Inkling Small measured |
| Mystery game puzzles | Not measured | 6.0% | Only Inkling Small measured |
| LMArena Text: hard prompts | Not measured | 1423 | Only Inkling Small measured |
| LMArena Text: expert | Not measured | 1441 | Only Inkling Small measured |
| LMArena Text: hard prompts in English | Not measured | 1429 | Only Inkling Small measured |
| LMArena Vision: diagrams | Not measured | 1251 | Only Inkling Small measured |
| LMArena Vision: homework | Not measured | 1257 | Only Inkling Small measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 90.0% | Only Inkling Small measured |
| FrontierMath, tiers 1 to 3 | Not measured | 46.3% | Only Inkling Small measured |
| FrontierMath, tier 4 | Not measured | 17.1% | Only Inkling Small measured |
| ProofBench | 75.0% | 6.0% | Hy4 preview |
| LMArena Text: math | Not measured | 1459 | Only Inkling Small measured |
| LMArena Text: mathematical work | Not measured | 1441 | Only Inkling Small 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 Small | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 85.6% | Only Inkling Small measured |
| LegalBench (Vals AI) | 83.8% | 83.0% | Hy4 preview |
| CorpFin (Vals AI) | Not measured | 69.6% | Only Inkling Small measured |
| TaxEval (Vals AI) | Not measured | 75.5% | Only Inkling Small measured |
| MortgageTax (Vals AI) | Not measured | 62.3% | Only Inkling Small measured |
| MedCode (Vals AI) | 43.3% | 37.9% | Hy4 preview |
| SimpleQA Verified | Not measured | 19.1% | Only Inkling Small measured |
| LMArena Text: science | Not measured | 1428 | Only Inkling Small measured |
| LMArena Text: medicine and healthcare | Not measured | 1413 | Only Inkling Small measured |
| LMArena Text: legal and government | Not measured | 1415 | Only Inkling Small measured |
| LMArena Text: business and finance | Not measured | 1413 | Only Inkling Small measured |
| Neither model has a result on the other 7 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Hy4 preview | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | 53.2% | 27.6% | Hy4 preview |
| Public Benefits Bench (Vals AI) | 68.6% | 59.4% | Hy4 preview |
| SAGE (Vals AI) | Not measured | 32.7% | Only Inkling Small measured |
| MedScribe (Vals AI) | 83.6% | 84.1% | Inkling Small |
| Vals Multimodal Index | Not measured | 50.0% | Only Inkling Small measured |
| Long context reasoning (AA-LCR) | Not measured | 75.7% | Only Inkling Small measured |
| LMArena Text | Not measured | 1413 | Only Inkling Small measured |
| LMArena Text: instruction following | Not measured | 1399 | Only Inkling Small measured |
| LMArena Text: creative writing | Not measured | 1334 | Only Inkling Small measured |
| LMArena Vision | Not measured | 1237 | Only Inkling Small measured |
| LMArena Text: English | Not measured | 1421 | Only Inkling Small measured |
| LMArena Text: non-English | Not measured | 1401 | Only Inkling Small measured |
| LMArena Text: Chinese | Not measured | 1464 | Only Inkling Small measured |
| LMArena Text: German | Not measured | 1408 | Only Inkling Small measured |
| LMArena Text: Japanese | Not measured | 1401 | Only Inkling Small measured |
| LMArena Text: Korean | Not measured | 1367 | Only Inkling Small measured |
| LMArena Text: French | Not measured | 1435 | Only Inkling Small measured |
| LMArena Text: Spanish | Not measured | 1422 | Only Inkling Small measured |
| LMArena Text: Russian | Not measured | 1394 | Only Inkling Small measured |
| LMArena Text: Polish | Not measured | 1428 | Only Inkling Small measured |
| LMArena Text: multi-turn | Not measured | 1416 | Only Inkling Small measured |
| LMArena Text: longer queries | Not measured | 1402 | Only Inkling Small measured |
| LMArena Text: writing and language | Not measured | 1357 | Only Inkling Small measured |
| LMArena Text: entertainment and media | Not measured | 1352 | Only Inkling Small measured |
| LMArena Vision: English | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: Chinese | Not measured | 1292 | Only Inkling Small measured |
| LMArena Vision: reading text | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: humor | Not measured | 1207 | Only Inkling Small measured |
| LMArena Vision: creative writing | Not measured | 1205 | Only Inkling Small measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | Inkling Small | 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
Inkling Small costs less
Repository review
50K input + 3K output tokens
Inkling Small costs less
Agent loop
200K input + 10K output tokens
Inkling Small 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 Small |
|---|---|---|
| Maker | Tencent | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | August 28, 2026 | July 30, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.834 | $0.45 |
| Output $/Mtok | $2.501 | $1.20 |
| Coding index | 44.3 | 27.3 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | Not computable | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 preview better than Inkling Small for coding?
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4. Pick Inkling Small for output tokens 2.1x cheaper ($1.20 vs $2.501 per million) and work measured by ProgramBench (Vals AI) or MedScribe (Vals AI), where it leads.
Which is cheaper, Hy4 preview or Inkling Small?
Hy4 preview costs $0.834 per million input tokens and $2.501 per million output tokens; Inkling Small costs $0.45 and $1.20. Cost per solved task is known for Inkling Small only.
Which has the bigger context window, Hy4 preview or Inkling Small?
Hy4 preview, with 1.05M tokens against 524K.
How many benchmarks is the Hy4 preview vs Inkling Small comparison based on?
21 benchmarks have a result for both models as of October 22, 2026. Hy4 preview's coding index rests on 3 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.