Skip to main content
BenchLM
Advertise

Model comparison

DeepSeek V4 Flash Base vs Inkling-Small

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

DeepSeek V4 Flash Base

DeepSeek

—

Evidence status unavailable

90% interval unavailable

Inkling-Small

Thinking Machines Lab

—

Evidence status unavailable

90% interval unavailable

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 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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • 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

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
0
DeepSeek V4 Flash Base only
24
Inkling-Small only
20
Like-for-like categories
0 / 8

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

Not comparable
DeepSeek V4 Flash Base
Not measured
Inkling-Small
70.1
Weighted basis
0 vs 2 rows
Reading
Not comparable

Coding

Not comparable
DeepSeek V4 Flash Base
Not measured
Inkling-Small
62.4
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
DeepSeek V4 Flash Base
44.7
Inkling-Small
40.1
Weighted basis
1 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
DeepSeek V4 Flash Base
56.4
Inkling-Small
53.4
Weighted basis
3 vs 2 rows
Reading
Not comparable

Math

Not comparable
DeepSeek V4 Flash Base
Not measured
Inkling-Small
92.9
Weighted basis
0 vs 2 rows
Reading
Not comparable

Multilingual

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

Multimodal

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

Instruction following

Not comparable
DeepSeek V4 Flash Base
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.

A shared-evidence shape is not available.

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

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 Flash Base
API rate not published
Fits in one request
Inkling-Small
$0.0013
Fits in one request

DeepSeek V4 Flash Base has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

DeepSeek V4 Flash Base
API rate not published
Fits in one request
Inkling-Small
$0.03332
Fits in one request

DeepSeek V4 Flash Base has no comparable published API token rate.

Cache-heavy agent loop

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

DeepSeek V4 Flash Base
API rate not published
Fits in one request
Cached-input rate unavailable
Inkling-Small
$0.0492
Fits in one request

DeepSeek V4 Flash Base has no comparable published API token rate.

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.

DeepSeek V4 Flash Base

1M

DeepSeek models and pricing

Inkling-Small

1M

Cached-input rate

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

DeepSeek V4 Flash Base

No comparable hosted API rate

Inkling-Small

$0.116 per 1M cached input tokens

Provider availability

DeepSeek V4 Flash Base

Generally Available · DeepSeek API, open weights

DeepSeek V4 release

Inkling-Small

Not sourced

Reasoning profile

DeepSeek V4 Flash Base

Non-Reasoning

Inkling-Small

Hybrid

Weight access

DeepSeek V4 Flash Base

Open Weight

Inkling-Small

Open Weight

License

DeepSeek V4 Flash Base

Open Weight

Inkling-Small

Open Weight

Release date

DeepSeek V4 Flash Base

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
A complete comparable API-rate estimate is not available for both models.
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 evidence44 rows

Agentic

  • Terminal-Bench 2.0

    DeepSeek V4 Flash Base—
    Inkling-Small64.7%
    Source

    Not directly comparable

  • BrowseComp

    DeepSeek V4 Flash Base—
    Inkling-Small77.4%
    Source

    Not directly comparable

  • MCP Atlas

    DeepSeek V4 Flash Base—
    Inkling-Small79.6%
    Source

    Not directly comparable

  • Toolathlon-Verified

    DeepSeek V4 Flash Base—
    Inkling-Small54.4%
    Source

    Not directly comparable

Coding

  • BigCodeBench

    DeepSeek V4 Flash Base56.8%
    Source
    Inkling-Small—

    Not directly comparable

  • HumanEval

    DeepSeek V4 Flash Base69.5%
    Source
    Inkling-Small—

    Not directly comparable

  • SWE-bench Verified

    DeepSeek V4 Flash Base—
    Inkling-Small80.2%
    Source

    Not directly comparable

  • SWE-bench Pro

    DeepSeek V4 Flash Base—
    Inkling-Small55.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    DeepSeek V4 Flash Base—
    Inkling-Small64.7%
    Source

    Not directly comparable

  • SciCode

    DeepSeek V4 Flash Base—
    Inkling-Small48.7%
    Source

    Not directly comparable

Reasoning

  • BBH

    DeepSeek V4 Flash Base86.9%
    Source
    Inkling-Small—

    Not directly comparable

  • DROP

    DeepSeek V4 Flash Base88.6%
    Source
    Inkling-Small—

    Not directly comparable

  • HellaSwag

    DeepSeek V4 Flash Base85.7%
    Source
    Inkling-Small—

    Not directly comparable

  • WinoGrande

    DeepSeek V4 Flash Base79.5%
    Source
    Inkling-Small—

    Not directly comparable

  • CLUEWSC

    DeepSeek V4 Flash Base82.2%
    Source
    Inkling-Small—

    Not directly comparable

  • LongBench v2

    DeepSeek V4 Flash Base44.7%
    Source
    Inkling-Small—

    Not directly comparable

  • ARC-AGI-2

    DeepSeek V4 Flash Base—
    Inkling-Small40.1%
    Source

    Not directly comparable

  • CritPt

    DeepSeek V4 Flash Base—
    Inkling-Small8.3%
    Source

    Not directly comparable

Knowledge

  • AGIEval

    DeepSeek V4 Flash Base82.6%
    Source
    Inkling-Small—

    Not directly comparable

  • MMLU

    DeepSeek V4 Flash Base88.7%
    Source
    Inkling-Small—

    Not directly comparable

  • MMLU-Redux

    DeepSeek V4 Flash Base89.4%
    Source
    Inkling-Small—

    Not directly comparable

  • MMLU-Pro

    DeepSeek V4 Flash Base68.3%
    Source
    Inkling-Small—

    Not directly comparable

  • MMMLU

    DeepSeek V4 Flash Base88.8%
    Source
    Inkling-Small—

    Not directly comparable

  • C-Eval

    DeepSeek V4 Flash Base92.1%
    Source
    Inkling-Small—

    Not directly comparable

  • CMMLU

    DeepSeek V4 Flash Base90.4%
    Source
    Inkling-Small—

    Not directly comparable

  • MultiLoKo

    DeepSeek V4 Flash Base42.2%
    Source
    Inkling-Small—

    Not directly comparable

  • SimpleQA

    DeepSeek V4 Flash Base30.1%
    Source
    Inkling-Small—

    Not directly comparable

  • SuperGPQA

    DeepSeek V4 Flash Base46.5%
    Source
    Inkling-Small—

    Not directly comparable

  • FACTS Parametric

    DeepSeek V4 Flash Base33.9%
    Source
    Inkling-Small—

    Not directly comparable

  • TriviaQA

    DeepSeek V4 Flash Base82.8%
    Source
    Inkling-Small—

    Not directly comparable

  • GPQA

    DeepSeek V4 Flash Base—
    Inkling-Small89.5%
    Source

    Not directly comparable

  • GPQA-D

    DeepSeek V4 Flash Base—
    Inkling-Small89.5%
    Source

    Not directly comparable

  • HLE

    DeepSeek V4 Flash Base—
    Inkling-Small47.8%
    Source

    Not directly comparable

  • HLE w/o tools

    DeepSeek V4 Flash Base—
    Inkling-Small31.6%
    Source

    Not directly comparable

Math

  • GSM8K

    DeepSeek V4 Flash Base90.8%
    Source
    Inkling-Small—

    Not directly comparable

  • MATH

    DeepSeek V4 Flash Base57.4%
    Source
    Inkling-Small—

    Not directly comparable

  • CMath

    DeepSeek V4 Flash Base93.6%
    Source
    Inkling-Small—

    Not directly comparable

  • AIME26

    DeepSeek V4 Flash Base—
    Inkling-Small95.5%
    Source

    Not directly comparable

  • HMMT Feb 2026

    DeepSeek V4 Flash Base—
    Inkling-Small90.2%
    Source

    Not directly comparable

Multilingual

  • MGSM

    DeepSeek V4 Flash Base85.7%
    Source
    Inkling-Small—

    Not directly comparable

Multimodal

  • MMMU-Pro

    DeepSeek V4 Flash Base—
    Inkling-Small74%
    Source

    Not directly comparable

  • CharXiv

    DeepSeek V4 Flash Base—
    Inkling-Small81.3%
    Source

    Not directly comparable

  • CharXiv w/o tools

    DeepSeek V4 Flash Base—
    Inkling-Small77.4%
    Source

    Not directly comparable

Instruction following

  • IFBench

    DeepSeek V4 Flash Base—
    Inkling-Small82.2%
    Source

    Not directly comparable

Frequently asked questions

Which is better, DeepSeek V4 Flash Base or Inkling-Small?

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, DeepSeek V4 Flash Base or Inkling-Small?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

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

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, DeepSeek V4 Flash Base or Inkling-Small?

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, DeepSeek V4 Flash Base 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 Flash Base 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.