Hy4 preview vs Inkling 2 Small
Inkling 2 Small leads Hy4 preview on coding, 48.9 to 44.3 on the Vibe Coding Index, and Inkling 2 Small costs 2.5x less per output token ($1.00 vs $2.501 per million). Updated November 14, 2026; 14 benchmarks have a result for both.
Hy4 preview or Inkling 2 Small: which to pick
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 44.3 for Hy4 preview.
Pick Hy4 preview for work measured by SREBench (Vals AI), where it leads.
- Shared results
- 14
- Hy4 preview only
- 11
- Inkling 2 Small only
- 37
- Like-for-like categories
- 3 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
Inkling 2 Small
Inkling 2 Small scores 48.9 against 44.3.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only Inkling 2 Small has a AA Intelligence Index result, 30.6.
Directional only
General
Vals Index
Inkling 2 Small
Inkling 2 Small leads, 56.1% against 53.2%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
Hy4 preview $0.0021, Inkling 2 Small $0.0008 per turn.
List prices
At a glance
- Coding index
- Hy4 preview 44.3 from 3 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- Agentic work, 3.9 points apart on average over 6 shared benchmarks.
- Widest single gap
- Harvey's Legal Agent Benchmark (Vals AI): Hy4 preview 8.8% against Inkling 2 Small 21.7%, 12.9 points apart on a 0 to 100 scale.
- Output price
- Hy4 preview $2.501 against Inkling 2 Small $1.00 per million output tokens, 2.5x apart.
- Context window
- Both take 1.05M 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 | Hy4 preview | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Agentic work | 1 | 5 | ||
| General | 0 | 1 | ||
| All shared boards | 1 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| LMArena WebDev | 1632 | 1647 | Inkling 2 Small |
| Terminal-Bench 4 (Vals AI) | 8.1% | 12.6% | Inkling 2 Small |
| Vibe Code Bench (Vals AI) | 77.5% | 81.5% | Inkling 2 Small |
| Code migration (Vals AI) | 47.4% | Not measured | Only Hy4 preview measured |
| ProgramBench (Vals AI) | 0.0% | 0.5% | Inkling 2 Small |
| IOI (Vals AI) | 59.3% | Not measured | Only Hy4 preview measured |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | Not measured | Only Hy4 preview measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 43.1% | Only Inkling 2 Small measured |
| CyberBench (Vals AI) | 65.4% | 72.7% | Inkling 2 Small |
| SciCode | Not measured | 52.3% | Only Inkling 2 Small measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | Not measured | 13.1% | Only Inkling 2 Small measured |
| FrontierCode 2.0 | Not measured | 25.4% | Only Inkling 2 Small measured |
| LMArena Text: coding | Not measured | 1455 | Only Inkling 2 Small measured |
| LMArena Text: software and IT | Not measured | 1443 | Only Inkling 2 Small measured |
| LMArena WebDev: React | 1653 | 1660 | Inkling 2 Small |
| LMArena WebDev: HTML | 1625 | 1661 | Inkling 2 Small |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 60.8 | Not measured | Only Hy4 preview measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 30.6 | Only Inkling 2 Small measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| SREBench (Vals AI) | 2.3% | 1.9% | Hy4 preview |
| Finance Agent (Vals AI) | 55.1% | Not measured | Only Hy4 preview measured |
| Tax Agent Bench (Vals AI) | 32.6% | 38.9% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 45.2% | 46.6% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | 8.8% | 21.7% | Inkling 2 Small |
| Excel Modeling Benchmark (Vals AI) | 58.1% | Not measured | Only Hy4 preview measured |
| BioMysteryBench (Vals AI) | 69.3% | 70.0% | Inkling 2 Small |
| Terminal-Bench-Science (Vals AI) | 1.4% | 2.9% | Inkling 2 Small |
| Vals Science Index | Not measured | 32.7% | Only Inkling 2 Small measured |
| APEX-Agents | Not measured | 46.8% | Only Inkling 2 Small measured |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | Not measured | 25.2% | Only Inkling 2 Small measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 44.1% | Only Inkling 2 Small measured |
| HLE-Diamond (Artificial Analysis run) | Not measured | 28.7% | Only Inkling 2 Small measured |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 35.0% | Only Inkling 2 Small measured |
| ARC-AGI | Not measured | 96.5% | Only Inkling 2 Small measured |
| ARC-AGI-2 | Not measured | 81.7% | Only Inkling 2 Small measured |
| LMArena Text: hard prompts | Not measured | 1421 | Only Inkling 2 Small measured |
| LMArena Text: expert | Not measured | 1478 | Only Inkling 2 Small measured |
| LMArena Text: hard prompts in English | Not measured | 1424 | Only Inkling 2 Small measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| ProofBench | 75.0% | Not measured | Only Hy4 preview measured |
| MathArena | Not measured | 42.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 83.8% | Not measured | Only Hy4 preview measured |
| MedCode (Vals AI) | 43.3% | Not measured | Only Hy4 preview measured |
| AA-Omniscience | Not measured | 16.1 | Only Inkling 2 Small measured |
| LMArena Text: science | Not measured | 1409 | Only Inkling 2 Small measured |
| LMArena Text: business and finance | Not measured | 1415 | Only Inkling 2 Small measured |
| Neither model has a result on the other 16 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Hy4 preview | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | 53.2% | 56.1% | Inkling 2 Small |
| Public Benefits Bench (Vals AI) | 68.6% | Not measured | Only Hy4 preview measured |
| SAGE (Vals AI) | Not measured | 88.6% | Only Inkling 2 Small measured |
| MedScribe (Vals AI) | 83.6% | Not measured | Only Hy4 preview measured |
| Long context reasoning (AA-LCR) | Not measured | 83.3% | Only Inkling 2 Small measured |
| GDPval-AA | Not measured | 1630 | Only Inkling 2 Small measured |
| LMArena Text | Not measured | 1403 | Only Inkling 2 Small measured |
| LMArena Text: instruction following | Not measured | 1408 | Only Inkling 2 Small measured |
| LMArena Text: creative writing | Not measured | 1348 | Only Inkling 2 Small measured |
| LMArena Text: English | Not measured | 1418 | Only Inkling 2 Small measured |
| LMArena Text: non-English | Not measured | 1390 | Only Inkling 2 Small measured |
| LMArena Text: Russian | Not measured | 1377 | Only Inkling 2 Small measured |
| LMArena Text: multi-turn | Not measured | 1408 | Only Inkling 2 Small measured |
| LMArena Text: longer queries | Not measured | 1403 | Only Inkling 2 Small measured |
| LMArena Text: writing and language | Not measured | 1381 | Only Inkling 2 Small measured |
| LMArena Text: entertainment and media | Not measured | 1359 | Only Inkling 2 Small measured |
| Neither model has a result on the other 33 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | Inkling 2 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 2 Small costs less
Repository review
50K input + 3K output tokens
Inkling 2 Small costs less
Agent loop
200K input + 10K output tokens
Inkling 2 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 2 Small |
|---|---|---|
| Maker | Tencent | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | August 28, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.834 | $0.30 |
| Output $/Mtok | $2.501 | $1.00 |
| Coding index | 44.3 | 48.9 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 preview better than Inkling 2 Small for coding?
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 44.3 for Hy4 preview. Pick Hy4 preview for work measured by SREBench (Vals AI), where it leads.
Which is cheaper, Hy4 preview or Inkling 2 Small?
Hy4 preview costs $0.834 per million input tokens and $2.501 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Hy4 preview or Inkling 2 Small?
Neither: both take 1.05M tokens.
How many benchmarks is the Hy4 preview vs Inkling 2 Small comparison based on?
14 benchmarks have a result for both models as of November 14, 2026. Hy4 preview's coding index rests on 3 independent benchmarks and Inkling 2 Small's on 3. Where only one model has a result, the page says so instead of naming a winner.