Skip to main content
BenchLM
Advertise

Model comparison

DeepSeek V4 Pro vs Inkling-Small

Updated July 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

DeepSeek V4 Pro

DeepSeek

60.0/100

Supported · Public rank #49

90% interval 41.6–78.3

Inkling-Small

Thinking Machines Lab

—

Evidence status unavailable

90% interval unavailable

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

9 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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

    DeepSeek V4 Pro

    DeepSeek V4 Pro 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

    DeepSeek V4 Pro

    DeepSeek V4 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    DeepSeek V4 Pro

    DeepSeek V4 Pro 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

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

What is actually comparable

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

Shared results
9
DeepSeek V4 Pro only
14
Inkling-Small only
11
Like-for-like categories
0 / 8

4 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Directional only
DeepSeek V4 Pro
59.1
Inkling-Small
70.1
Weighted basis
1 vs 2 rows
Reading
Directional only

Coding

Directional only
DeepSeek V4 Pro
65.3
Inkling-Small
62.4
Weighted basis
2 vs 3 rows
Reading
Directional only

Knowledge

Directional only
DeepSeek V4 Pro
41.3
Inkling-Small
53.4
Weighted basis
4 vs 2 rows
Reading
Directional only

Math

Directional only
DeepSeek V4 Pro
31.7
Inkling-Small
92.9
Weighted basis
1 vs 2 rows
Reading
Directional only

Reasoning

Not comparable
DeepSeek V4 Pro
Not measured
Inkling-Small
40.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
DeepSeek V4 Pro
Not measured
Inkling-Small
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
DeepSeek V4 Pro
Not measured
Inkling-Small
76.6
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
DeepSeek V4 Pro
Not measured
Inkling-Small
82.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

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.

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

DeepSeek V4 Pro
$0.00087
Fits in one request
Inkling-Small
$0.0013
Fits in one request

DeepSeek V4 Pro has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

DeepSeek V4 Pro
$0.02436
Fits in one request
Inkling-Small
$0.03332
Fits in one request

DeepSeek V4 Pro has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

DeepSeek V4 Pro
$0.01812
Fits in one request
Inkling-Small
$0.0492
Fits in one request

DeepSeek V4 Pro has the lower modeled cost

Costs use the listed standard API rates.

Specification differences

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

Cached-input rate

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

DeepSeek V4 Pro

$0.003625 per 1M cached input tokens

Inkling-Small

$0.116 per 1M cached input tokens

Provider availability

DeepSeek V4 Pro

Generally Available · DeepSeek API, open weights

DeepSeek V4 release

Inkling-Small

Not sourced

Reasoning profile

DeepSeek V4 Pro

Non-Reasoning

Inkling-Small

Hybrid

Weight access

DeepSeek V4 Pro

Open Weight

Inkling-Small

Open Weight

License

DeepSeek V4 Pro

Open Weight

Inkling-Small

Open Weight

Release date

DeepSeek V4 Pro

2026-04-24

Inkling-Small

2026-07-30

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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
Repository review: $0.02436 vs $0.03332. Cache-heavy agent loop: $0.01812 vs $0.0492.
Context tradeoff
Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

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

Browse raw public benchmark evidence34 rows

Agentic

  • Terminal-Bench 2.0

    DeepSeek V4 Pro59.1%
    Source
    Inkling-Small64.7%
    Source

    Inkling-Small leads this result

  • MCP Atlas

    DeepSeek V4 Pro69.4%
    Source
    Inkling-Small79.6%
    Source

    Inkling-Small leads this result

  • Toolathlon

    DeepSeek V4 Pro46.3%
    Source
    Inkling-Small—

    Not directly comparable

  • Claw-Eval

    DeepSeek V4 Pro59.8%
    Source
    Inkling-Small—

    Not directly comparable

  • Gert Labs

    DeepSeek V4 Pro50.28%
    Source
    Inkling-Small—

    Not directly comparable

  • ResearchClawBench

    DeepSeek V4 Pro17.1%
    Source
    Inkling-Small—

    Not directly comparable

  • BrowseComp

    DeepSeek V4 Pro—
    Inkling-Small77.4%
    Source

    Not directly comparable

  • Toolathlon-Verified

    DeepSeek V4 Pro—
    Inkling-Small54.4%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pass@1-COT

    DeepSeek V4 Pro56.8%
    Source
    Inkling-Small—

    Not directly comparable

  • SWE-bench Verified

    DeepSeek V4 Pro73.6%
    Source
    Inkling-Small80.2%
    Source

    Inkling-Small leads this result

  • SWE-bench Pro

    DeepSeek V4 Pro52.1%
    Source
    Inkling-Small55.9%
    Source

    Inkling-Small leads this result

  • SWE Multilingual

    DeepSeek V4 Pro69.8%
    Source
    Inkling-Small—

    Not directly comparable

  • Terminal-Bench 2.0

    DeepSeek V4 Pro59.1%
    Source
    Inkling-Small64.7%
    Source

    Inkling-Small leads this result

  • SciCode

    DeepSeek V4 Pro—
    Inkling-Small48.7%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    DeepSeek V4 Pro44.7%
    Source
    Inkling-Small—

    Not directly comparable

  • CorpusQA 1M

    DeepSeek V4 Pro35.6%
    Source
    Inkling-Small—

    Not directly comparable

  • ARC-AGI-2

    DeepSeek V4 Pro—
    Inkling-Small40.1%
    Source

    Not directly comparable

  • CritPt

    DeepSeek V4 Pro—
    Inkling-Small8.3%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    DeepSeek V4 Pro82.9%
    Source
    Inkling-Small—

    Not directly comparable

  • SimpleQA

    DeepSeek V4 Pro45%
    Source
    Inkling-Small—

    Not directly comparable

  • Chinese-SimpleQA

    DeepSeek V4 Pro75.8%
    Source
    Inkling-Small—

    Not directly comparable

  • GPQA

    DeepSeek V4 Pro72.9%
    Source
    Inkling-Small89.5%
    Source

    Inkling-Small leads this result

  • GPQA-D

    DeepSeek V4 Pro72.9%
    Source
    Inkling-Small89.5%
    Source

    Inkling-Small leads this result

  • HLE

    DeepSeek V4 Pro7.7%
    Source
    Inkling-Small47.8%
    Source

    Inkling-Small leads this result

  • HLE w/o tools

    DeepSeek V4 Pro—
    Inkling-Small31.6%
    Source

    Not directly comparable

Math

  • HMMT Feb 2026

    DeepSeek V4 Pro31.7%
    Source
    Inkling-Small90.2%
    Source

    Inkling-Small leads this result

  • IMOAnswerBench

    DeepSeek V4 Pro35.3%
    Source
    Inkling-Small—

    Not directly comparable

  • Apex

    DeepSeek V4 Pro0.4%
    Source
    Inkling-Small—

    Not directly comparable

  • Apex Shortlist

    DeepSeek V4 Pro9.2%
    Source
    Inkling-Small—

    Not directly comparable

  • AIME26

    DeepSeek V4 Pro—
    Inkling-Small95.5%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    DeepSeek V4 Pro—
    Inkling-Small74%
    Source

    Not directly comparable

  • CharXiv

    DeepSeek V4 Pro—
    Inkling-Small81.3%
    Source

    Not directly comparable

  • CharXiv w/o tools

    DeepSeek V4 Pro—
    Inkling-Small77.4%
    Source

    Not directly comparable

Instruction following

  • IFBench

    DeepSeek V4 Pro—
    Inkling-Small82.2%
    Source

    Not directly comparable

Frequently asked questions

Which is better, DeepSeek V4 Pro or Inkling-Small?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, DeepSeek V4 Pro or Inkling-Small?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, DeepSeek V4 Pro or Inkling-Small?

The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which costs less, DeepSeek V4 Pro or Inkling-Small?

For the stated presets, chat costs $0.00087 on DeepSeek V4 Pro and $0.0013 on Inkling-Small; repository review costs $0.02436 and $0.03332; the cache-heavy agent loop costs $0.01812 and $0.0492. Costs use the listed standard API rates.

Which has the larger context window, DeepSeek V4 Pro or Inkling-Small?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 30, 2026

Watch DeepSeek V4 Pro vs Inkling-Small

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

Read a sample issue

Join 2,000+ readers.