Skip to main content
BenchLM
Data

Hy3 Preview vs Inkling 2 Mini

Updated November 21, 2026. Rank says Inkling 2 Mini is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Inkling 2 Mini has the higher public point estimate, 55.9 versus 38.5. Their conditional score ranges overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Tencent logo

Tencent

38.5/100

Estimated · Public rank #164

Conditional range 23.7–53.3

Model B
Thinking Machines Lab logo

Thinking Machines Lab

55.9/100

Estimated · Public rank #69

Conditional range 46.0–65.9

API price per 1M tokens

Hy3 Preview: No comparable API price

Inkling 2 Mini: $0.15 input / $0.50 output

Context window

Hy3 Preview: 256K

Inkling 2 Mini: 1M

Released

Hy3 Preview: April 23, 2026

Inkling 2 Mini: November 20, 2026

Shared results
3
Hy3 Preview only
3
Inkling 2 Mini only
30
Like-for-like categories
0 / 8
Estimated: Hy3 Preview and Inkling 2 Mini. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    Inkling 2 Mini

    Inkling 2 Mini has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Hy3 Preview is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Hy3 Preview and Inkling 2 Mini are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

—Hy3 Preview53.9Inkling 2 Mini

Not comparable · BenchAlign v6.0

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
Hy3 Preview
36.0
Estimated · #153/179
Inkling 2 Mini
59.1
Estimated · #61/179
Basis
BenchAlign v6.0 lane · 2 vs 8 public rows
Reading
Directional only

Reasoning

Directional only
Hy3 Preview
37.1
Estimated · #151/161
Inkling 2 Mini
57.8
Estimated · #58/161
Basis
BenchAlign v6.0 lane · 0 vs 2 public rows
Reading
Directional only

Knowledge

Directional only
Hy3 Preview
39.1
Estimated · #133/158
Inkling 2 Mini
51.9
Estimated · #79/158
Basis
BenchAlign v6.0 lane · 2 vs 3 public rows
Reading
Directional only

Coding

Not comparable
Hy3 Preview
Not ranked
Inkling 2 Mini
53.9
Estimated · #67/179
Basis
BenchAlign v6.0 lane · 2 vs 5 public rows
Reading
Not comparable

Multimodal

Not comparable
Hy3 Preview
Not ranked
Inkling 2 Mini
55.5
Estimated · #62/119
Basis
BenchAlign v6.0 lane · 0 vs 13 public rows
Reading
Not comparable

Multilingual

Not comparable
Hy3 Preview
Not ranked
Inkling 2 Mini
54.7
Estimated · #39/87
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Instruction following

Not comparable
Hy3 Preview
Not ranked
Inkling 2 Mini
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
Not comparable

Math

Not comparable
Hy3 Preview
Not ranked
Inkling 2 Mini
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Inkling 2 Mini
$0.0004
Fits in one request

Hy3 Preview has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Inkling 2 Mini
$0.009
Fits in one request

Hy3 Preview has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable
Inkling 2 Mini
$0.011
Fits in one request

Hy3 Preview has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 20, 2026.

Inkling 2 Mini

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • Hy3 Preview has no public API price, so it is not plotted.
  • 2 models at the same price score higher than Inkling 2 Mini. The nearest is Claude Haiku 5.5 (score 63.7, also $0.50 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Inkling 2 Mini on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

Hy3 Preview

256K

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Hy3 Preview

No comparable hosted API rate

Inkling 2 Mini

$0.015 per 1M cached input tokens

Tinker models and pricing

Provider availability

Hy3 Preview

Not sourced

Inkling 2 Mini

Not sourced

Reasoning profile

Hy3 Preview

Reasoning

Inkling 2 Mini

Hybrid

Weight access

Hy3 Preview

Open Weight

Inkling 2 Mini

Open Weight

License

Hy3 Preview

Open Weight

Inkling 2 Mini

Open Weight

Release date

Hy3 Preview

2026-04-23

Inkling 2 Mini

2026-11-20

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Inkling 2 Mini has the higher public point estimate, 55.9 versus 38.5. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Inkling 2 Mini has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Hy3 Preview or Inkling 2 Mini?

Inkling 2 Mini has the higher public point estimate, 55.9 versus 38.5. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Hy3 Preview or Inkling 2 Mini?

Hy3 Preview is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Hy3 Preview or Inkling 2 Mini?

Inkling 2 Mini scores higher for agentic tasks on the public lane, 59.1 to 36. Hy3 Preview and Inkling 2 Mini are scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Hy3 Preview or Inkling 2 Mini?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Hy3 Preview or Inkling 2 Mini?

Inkling 2 Mini has the larger documented context window: 1M, compared with 256K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence36 rows

Agentic

  • Terminal-Bench 2.0

    Hy3 Preview54.4%
    Source
    Inkling 2 Mini—

    Not directly comparable

  • Gert Labs

    Hy3 Preview36.91%
    Source
    Inkling 2 Mini—

    Not directly comparable

  • Terminal-Bench 4.0

    Hy3 Preview—
    Inkling 2 Mini5.60%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Hy3 Preview—
    Inkling 2 Mini71.6%
    Source

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Hy3 Preview—
    Inkling 2 Mini1.4%
    Source

    Not directly comparable

  • BrowseComp

    Hy3 Preview—
    Inkling 2 Mini79%
    Source

    Not directly comparable

  • DeepSearchQA

    Hy3 Preview—
    Inkling 2 Mini85.3%
    Source

    Not directly comparable

  • MCP Atlas

    Hy3 Preview—
    Inkling 2 Mini82.7%
    Source

    Not directly comparable

  • JobBench

    Hy3 Preview—
    Inkling 2 Mini49.6%
    Source

    Not directly comparable

  • EnterpriseOps-Gym

    Hy3 Preview—
    Inkling 2 Mini42.00%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Hy3 Preview74.4%
    Source
    Inkling 2 Mini79.2%
    Source

    Inkling 2 Mini leads this result

  • Terminal-Bench 2.0

    Hy3 Preview54.4%
    Source
    Inkling 2 Mini—

    Not directly comparable

  • FrontierCode 2.0

    Hy3 Preview—
    Inkling 2 Mini15.1%
    Source

    Not directly comparable

  • DeepSWE

    Hy3 Preview—
    Inkling 2 Mini48.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Hy3 Preview—
    Inkling 2 Mini71.6%
    Source

    Not directly comparable

  • SWE Multilingual

    Hy3 Preview—
    Inkling 2 Mini73.7%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Hy3 Preview—
    Inkling 2 Mini66.9%
    Source

    Not directly comparable

  • MRCR v2 256K-512K

    Hy3 Preview—
    Inkling 2 Mini46.4%
    Source

    Not directly comparable

Multimodal

  • PerceptionBench

    Hy3 Preview—
    Inkling 2 Mini57.5%
    Source

    Not directly comparable

  • MMMU-Pro

    Hy3 Preview—
    Inkling 2 Mini74.9%
    Source

    Not directly comparable

  • OmniDocBench 1.6

    Hy3 Preview—
    Inkling 2 Mini92.8%
    Source

    Not directly comparable

  • BabyVision

    Hy3 Preview—
    Inkling 2 Mini53.4%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Hy3 Preview—
    Inkling 2 Mini88.8%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Hy3 Preview—
    Inkling 2 Mini76.5%
    Source

    Not directly comparable

  • CharXiv

    Hy3 Preview—
    Inkling 2 Mini88.3%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Hy3 Preview—
    Inkling 2 Mini80.6%
    Source

    Not directly comparable

  • Chartography (no tools)

    Hy3 Preview—
    Inkling 2 Mini22.1%
    Source

    Not directly comparable

  • Chartography (tools)

    Hy3 Preview—
    Inkling 2 Mini72.5%
    Source

    Not directly comparable

  • ZeroBench

    Hy3 Preview—
    Inkling 2 Mini17.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Hy3 Preview—
    Inkling 2 Mini34.0%
    Source

    Not directly comparable

  • MathVision

    Hy3 Preview—
    Inkling 2 Mini89.0%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Hy3 Preview87.2%
    Source
    Inkling 2 Mini86.6%
    Source

    Hy3 Preview leads this result

  • GPQA-D

    Hy3 Preview87.2%
    Source
    Inkling 2 Mini86.6%
    Source

    Hy3 Preview leads this result

  • HLE w/o tools

    Hy3 Preview—
    Inkling 2 Mini30.7%
    Source

    Not directly comparable

Instruction following

  • MultiChallenge (provider reports)

    Hy3 Preview—
    Inkling 2 Mini50.00%
    Source

    Not directly comparable

Math

  • Apex

    Hy3 Preview—
    Inkling 2 Mini34.4%
    Source

    Not directly comparable

36 public results · 3 shared

Watch Hy3 Preview vs Inkling 2 Mini

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026