Skip to main content
BenchLM
Data

Inkling vs d1.2-ultra

Updated November 17, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead. 0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Thinking Machines Lab logo

Thinking Machines Lab

47.79/100

Supported · Public rank #108

90% interval 30.4–65.2

Model B
Liquid AI logo

Liquid AI

—

Evidence status unavailable

90% interval unavailable

API price per 1M tokens

Inkling: $1.87 input / $4.68 output

d1.2-ultra: $0.042 input / $0 output

Context window

Inkling: 1M

d1.2-ultra: Not sourced

Released

Inkling: July 15, 2026

d1.2-ultra: November 16, 2026

Shared results
0
Inkling only
25
d1.2-ultra only
0
Like-for-like categories
0 / 8
Supported: InklingHow 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    d1.2-ultra

    d1.2-ultra has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

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

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

    d1.2-ultra

    d1.2-ultra has the lower estimated token cost for this stated workload. d1.2-ultra has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback
Show secondary and unsupported calls
  • Repository review cost

    50K fresh input + 3K output tokens

    d1.2-ultra

    d1.2-ultra has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    D1.2-ultra 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

    D1.2-ultra is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Not enough matched evidence

    A complete context comparison is not sourced.

    Confidence: limited

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.

35.1Inkling—d1.2-ultra

Not comparable · BenchAlign v5.8

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.

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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Not comparable
Inkling
37.2
Supported · #82/138
d1.2-ultra
Not ranked
Basis
BenchAlign v5.8 lane · 6 vs 0 public rows
Reading
Not comparable

Coding

Not comparable
Inkling
35.1
Supported · #85/163
d1.2-ultra
Not ranked
Basis
BenchAlign v5.8 lane · 6 vs 0 public rows
Reading
Not comparable

Reasoning

Not comparable
Inkling
38.2
Estimated · #96/160
d1.2-ultra
Not ranked
Basis
BenchAlign v5.8 lane · 0 vs 0 public rows
Reading
Not comparable

Multimodal

Not comparable
Inkling
49.6
Estimated · #58/67
d1.2-ultra
Not ranked
Basis
BenchAlign v5.8 lane · 3 vs 0 public rows
Reading
Not comparable

Knowledge

Not comparable
Inkling
51.0
Supported · #77/181
d1.2-ultra
Not ranked
Basis
BenchAlign v5.8 lane · 6 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Inkling
Not ranked
d1.2-ultra
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Inkling
87.6
#40/157
d1.2-ultra
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Inkling
54.6
#9/12
d1.2-ultra
Not ranked
Basis
Provisional lane · 3 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · 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

Inkling
$0.00421
Fits in one request
d1.2-ultra
$0.00004
Fit state unavailable

d1.2-ultra has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Inkling
$0.10754
Fits in one request
d1.2-ultra
$0.0021
Fit state unavailable

d1.2-ultra has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Inkling
$0.159
Fits in one request
d1.2-ultra
$0.00924
Fit state unavailable
Cached input priced at the published list-input rate

d1.2-ultra has the lower modeled cost

d1.2-ultra has no published cached-input rate, so cached tokens use its listed input rate.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Inkling
$28.06
per month
d1.2-ultra
$0.420
per month

Standard listed rates, no batch or volume discounts.

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 17, 2026.

Inkling

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 26 cheaper models score at least as high as Inkling. The nearest is Qwen4 Max (score 65.0, $4.50 per 1M output tokens).
  • d1.2-ultra has no overall score yet, so it is not plotted.

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 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.

Inkling

1M

d1.2-ultra

Cached-input rate

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

Inkling

$0.374 per 1M cached input tokens

d1.2-ultra

Not published

Liquid AI pricing

Provider availability

Inkling

Not sourced

d1.2-ultra

Generally Available · Liquid API, Liquid Console

Liquid AI d1.2 launch

Reasoning profile

Inkling

Hybrid

d1.2-ultra

Non-Reasoning

Weight access

Inkling

Open Weight

d1.2-ultra

Proprietary

License

Inkling

Open Weight

d1.2-ultra

Proprietary

Release date

Inkling

2026-07-15

d1.2-ultra

2026-11-16

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.10754 vs $0.0021. Cache-heavy agent loop: $0.159 vs $0.00924.
Context tradeoff
A complete documented context comparison is not available.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Inkling or d1.2-ultra?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Inkling or d1.2-ultra?

D1.2-ultra is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Inkling or d1.2-ultra?

D1.2-ultra is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Inkling or d1.2-ultra?

For the stated presets, chat costs $0.00421 on Inkling and $0.00004 on d1.2-ultra; repository review costs $0.10754 and $0.0021; the cache-heavy agent loop costs $0.159 and $0.00924. d1.2-ultra has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Inkling or d1.2-ultra?

A complete documented context-window comparison is not available.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Inkling
API / mo$4,913
Self-host / mo$27,962
Break-evenNot reached at 70% load
d1.2-ultra
API / mo$32
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence25 rows

Agentic

  • Terminal-Bench 4.1

    Inkling0.00%
    Source
    d1.2-ultra—

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling63.8%
    Source
    d1.2-ultra—

    Not directly comparable

  • BrowseComp

    Inkling77.1%
    Source
    d1.2-ultra—

    Not directly comparable

  • MCP Atlas

    Inkling74.1%
    Source
    d1.2-ultra—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Inkling47.6%
    Source
    d1.2-ultra—

    Not directly comparable

  • CWE-bench v1

    Inkling37.0%
    Source
    d1.2-ultra—

    Not directly comparable

Coding

  • SWE-bench Verified

    Inkling77.6%
    Source
    d1.2-ultra—

    Not directly comparable

  • SWE-bench Pro

    Inkling54.3%
    Source
    d1.2-ultra—

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling63.8%
    Source
    d1.2-ultra—

    Not directly comparable

  • FrontierSWE v2

    Inkling4.1%
    Source
    d1.2-ultra—

    Not directly comparable

  • LiveCodeBench (Vals)

    Inkling85.5%
    Source
    d1.2-ultra—

    Not directly comparable

  • SWE-bench (Vals)

    Inkling77.6%
    Source
    d1.2-ultra—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Inkling73.5%
    Source
    d1.2-ultra—

    Not directly comparable

  • CharXiv

    Inkling82%
    Source
    d1.2-ultra—

    Not directly comparable

  • CharXiv w/o tools

    Inkling78.1%
    Source
    d1.2-ultra—

    Not directly comparable

Knowledge

  • GPQA

    Inkling87.9%
    Source
    d1.2-ultra—

    Not directly comparable

  • GPQA-D

    Inkling87.9%
    Source
    d1.2-ultra—

    Not directly comparable

  • HLE

    Inkling46%
    Source
    d1.2-ultra—

    Not directly comparable

  • HLE w/o tools

    Inkling30%
    Source
    d1.2-ultra—

    Not directly comparable

  • GPQA Diamond (Vals)

    Inkling87.1%
    Source
    d1.2-ultra—

    Not directly comparable

  • MMLU-Pro (Vals)

    Inkling86.3%
    Source
    d1.2-ultra—

    Not directly comparable

Instruction following

  • IFBench

    Inkling79.8%
    Source
    d1.2-ultra—

    Not directly comparable

Math

  • AIME26

    Inkling97.1%
    Source
    d1.2-ultra—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Inkling33.333%
    Source
    d1.2-ultra—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Inkling4.878%
    Source
    d1.2-ultra—

    Not directly comparable

25 public results · 0 shared

Watch Inkling vs d1.2-ultra

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 17, 2026