Enter opens the highlighted result. Esc closes.

Hy4 flash vs Inkling Small

Hy4 flash leads Inkling Small on coding, 44.5 to 27.3 on the Vibe Coding Index, and Hy4 flash costs 8.5x less per output token ($0.1405 vs $1.20 per million). Updated November 22, 2026; 7 benchmarks have a result for both.

Hy4 flashTencent
Coding
44.5
Overall
No data
Output $/M
$0.1405
7
T Inkling SmallThinking Machines
Coding
27.3
Overall
45.6
Output $/M
$1.20
0
vs boards won of 7 shared

Hy4 flash or Inkling Small: which to pick

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 27.3 for Inkling Small, though on 2 benchmarks against 4.

Inkling Small is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Shared results
7
Hy4 flash only
5
Inkling Small only
84
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.

At a glance

Coding index
Hy4 flash 44.5 from 2 benchmarks, Inkling Small 27.3 from 4 benchmarks.
Widest category
Coding, 31.1 points apart on average over 3 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Hy4 flash 74.8% against Inkling Small 19.1%, 55.8 points apart on a 0 to 100 scale.
Output price
Hy4 flash $0.1405 against Inkling Small $1.20 per million output tokens, 8.5x apart.
Context window
Hy4 flash 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.

Boards won, where both have a result
CategoryHy4 flashBarsInkling SmallTies
Coding30
Agentic work30
General10
All shared boards70
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
LMArena WebDevNot measured1408Only Inkling Small measured
LiveCodeBench (Vals AI)Not measured85.9%Only Inkling Small measured
SWE-bench Verified (Vals AI)Not measured82.2%Only Inkling Small measured
Terminal-Bench 4 (Vals AI)15.2%0.0%Hy4 flash
Vibe Code Bench (Vals AI)74.8%19.1%Hy4 flash
Code migration (Vals AI)Not measured13.7%Only Inkling Small measured
ProgramBench (Vals AI)Not measured0.5%Only Inkling Small measured
IOI (Vals AI)Not measured9.3%Only Inkling Small measured
Terminal-Bench 2.1 (Vals AI)Not measured55.1%Only Inkling Small measured
SkillsBench (Vals AI)Not measured33.6%Only Inkling Small measured
CyberBench (Vals AI)Not measured64.1%Only Inkling Small measured
SciCodeNot measured49.7%Only Inkling Small measured
Terminal-Bench 4.0 (Artificial Analysis run)Not measured1.0%Only Inkling Small measured
FrontierCode 2.0Not measured4.8%Only Inkling Small measured
LMArena Text: codingNot measured1452Only Inkling Small measured
LMArena Text: software and ITNot measured1448Only Inkling Small measured
LMArena WebDev: ReactNot measured1397Only Inkling Small measured
LMArena WebDev: HTMLNot measured1397Only Inkling Small measured
LMArena WebDev: from an imageNot measured1410Only Inkling Small measured
GameBench 250.533.1Hy4 flash
Terminal-Bench 4.0Not measured0.9%Only Inkling Small measured
Neither model has a result on the other 31 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
AA Intelligence IndexNot measured12.9Only Inkling Small measured
Epoch Capabilities IndexNot measured150.8Only Inkling Small measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
Finance Agent (Vals AI)Not measured41.3%Only Inkling Small measured
Tax Agent Bench (Vals AI)23.3%15.4%Hy4 flash
Legal Research Bench (Vals AI)38.5%25.5%Hy4 flash
Harvey's Legal Agent Benchmark (Vals AI)5.4%2.9%Hy4 flash
Excel Modeling Benchmark (Vals AI)Not measured31.8%Only Inkling Small measured
MCP AtlasNot measured79.2%Only Inkling Small measured
Toolathlon-VerifiedNot measured54.4%Only Inkling Small measured
Neither model has a result on the other 37 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
Reasoning benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
GPQA DiamondNot measured83.6%Only Inkling Small measured
GPQA Diamond (Artificial Analysis run)Not measured89.5%Only Inkling Small measured
Humanity's Last Exam (Artificial Analysis run)Not measured33.3%Only Inkling Small measured
HLE-Diamond (Artificial Analysis run)Not measured12.1%Only Inkling Small measured
CritPt v2, hard subset (Artificial Analysis run)Not measured18.5%Only Inkling Small measured
GPQA Diamond (Epoch AI run)Not measured88.5%Only Inkling Small measured
ARC-AGINot measured84.0%Only Inkling Small measured
ARC-AGI-2Not measured40.1%Only Inkling Small measured
Mystery game puzzlesNot measured6.0%Only Inkling Small measured
LMArena Text: hard promptsNot measured1425Only Inkling Small measured
LMArena Text: expertNot measured1441Only Inkling Small measured
LMArena Text: hard prompts in EnglishNot measured1429Only Inkling Small measured
LMArena Vision: diagramsNot measured1253Only Inkling Small measured
LMArena Vision: homeworkNot measured1251Only Inkling Small measured
Neither model has a result on the other 12 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
OTIS Mock AIMENot measured90.0%Only Inkling Small measured
FrontierMath, tiers 1 to 3Not measured46.3%Only Inkling Small measured
FrontierMath, tier 4Not measured17.1%Only Inkling Small measured
ProofBenchNot measured6.0%Only Inkling Small measured
LMArena Text: mathNot measured1459Only Inkling Small measured
LMArena Text: mathematical workNot measured1436Only Inkling Small measured
Neither model has a result on the other 8 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Knowledge benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
MMLU ProNot measured85.6%Only Inkling Small measured
LegalBench (Vals AI)Not measured83.0%Only Inkling Small measured
CorpFin (Vals AI)Not measured69.6%Only Inkling Small measured
TaxEval (Vals AI)Not measured75.5%Only Inkling Small measured
MortgageTax (Vals AI)Not measured62.3%Only Inkling Small measured
MedCode (Vals AI)Not measured37.9%Only Inkling Small measured
AA-OmniscienceNot measured-9.5Only Inkling Small measured
SimpleQA VerifiedNot measured19.1%Only Inkling Small measured
LMArena Text: scienceNot measured1429Only Inkling Small measured
LMArena Text: medicine and healthcareNot measured1414Only Inkling Small measured
LMArena Text: legal and governmentNot measured1414Only Inkling Small measured
LMArena Text: business and financeNot measured1413Only Inkling Small measured
Neither model has a result on the other 9 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
Design Arena: websites1227Not measuredOnly Hy4 flash measured
Design Arena: UI components1262Not measuredOnly Hy4 flash measured
Design Arena: game dev1202Not measuredOnly Hy4 flash measured
Design Arena: 3D1209Not measuredOnly Hy4 flash measured
Design Arena: all code categories1225Not measuredOnly Hy4 flash measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
General benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
Vals Index50.8%27.6%Hy4 flash
Public Benefits Bench (Vals AI)Not measured59.4%Only Inkling Small measured
MedScribe (Vals AI)Not measured84.1%Only Inkling Small measured
Vals Multimodal IndexNot measured50.0%Only Inkling Small measured
Long context reasoning (AA-LCR)Not measured75.7%Only Inkling Small measured
GDPval-AANot measured1133Only Inkling Small measured
LMArena TextNot measured1414Only Inkling Small measured
LMArena Text: instruction followingNot measured1402Only Inkling Small measured
LMArena Text: creative writingNot measured1338Only Inkling Small measured
LMArena VisionNot measured1236Only Inkling Small measured
LMArena Text: EnglishNot measured1421Only Inkling Small measured
LMArena Text: non-EnglishNot measured1402Only Inkling Small measured
LMArena Text: ChineseNot measured1462Only Inkling Small measured
LMArena Text: GermanNot measured1402Only Inkling Small measured
LMArena Text: JapaneseNot measured1399Only Inkling Small measured
LMArena Text: KoreanNot measured1384Only Inkling Small measured
LMArena Text: FrenchNot measured1438Only Inkling Small measured
LMArena Text: SpanishNot measured1436Only Inkling Small measured
LMArena Text: RussianNot measured1397Only Inkling Small measured
LMArena Text: PolishNot measured1427Only Inkling Small measured
LMArena Text: multi-turnNot measured1417Only Inkling Small measured
LMArena Text: longer queriesNot measured1403Only Inkling Small measured
LMArena Text: writing and languageNot measured1360Only Inkling Small measured
LMArena Text: entertainment and mediaNot measured1353Only Inkling Small measured
LMArena Vision: EnglishNot measured1244Only Inkling Small measured
LMArena Vision: ChineseNot measured1287Only Inkling Small measured
LMArena Vision: reading textNot measured1242Only Inkling Small measured
LMArena Vision: humorNot measured1199Only Inkling Small measured
LMArena Vision: creative writingNot measured1199Only Inkling Small 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
Image generation benchmarks for Hy4 flash and Inkling Small
BenchmarkHy4 flashInkling SmallLeader
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 flash$0.0001Fits in one request
Inkling Small$0.0010Fits in one request

Hy4 flash costs less

Repository review

50K input + 3K output tokens

Hy4 flash$0.0022Fits in one request
Inkling Small$0.026Fits in one request

Hy4 flash costs less

Agent loop

200K input + 10K output tokens

Hy4 flash$0.0084Fits in one request
Inkling Small$0.102Fits in one request

Hy4 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.

Specifications of Hy4 flash and Inkling Small
SpecificationTencent Hy4 flashThinking Machines Inkling Small
MakerTencentThinking Machines
WeightsOpen weightsOpen weights
ReleasedNovember 16, 2026July 30, 2026
Context window1.05M524K
Input $/Mtok$0.035$0.45
Output $/Mtok$0.1405$1.20
Coding index44.527.3
Independent measurements behind it24
Cost per solved taskNot computable$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is Hy4 flash better than Inkling Small for coding?

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 27.3 for Inkling Small, though on 2 benchmarks against 4. Inkling Small is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Which is cheaper, Hy4 flash or Inkling Small?

Hy4 flash costs $0.035 per million input tokens and $0.1405 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 flash or Inkling Small?

Hy4 flash, with 1.05M tokens against 524K.

How many benchmarks is the Hy4 flash vs Inkling Small comparison based on?

7 benchmarks have a result for both models as of November 22, 2026. Hy4 flash's coding index rests on 2 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/tencent-hy4-flash-vs-thinkingmachines-inkling-small" title="Hy4 flash vs Inkling Small, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/tencent-hy4-flash-vs-thinkingmachines-inkling-small">LLMBenchmark.ai, Hy4 flash vs Inkling Small</a></p>