Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM
Thinking Machines Lab logo
Model A
Inkling

Thinking Machines Lab

60.28/100

Supported · Public rank #65

90% interval 50.5–70.1

Inkling vs LFM2.5-VL-3B

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

LiquidAI logo
Model B
LFM2.5-VL-3B

LiquidAI

—

Evidence status unavailable

90% interval unavailable

Decision reading

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

2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on XLinkedInSocial cardCSVJSON

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

    Inkling 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

    LFM2.5-VL-3B 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

    LFM2.5-VL-3B is not ranked on the public lane for agentic, so no winner is named for agentic.

    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

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. LFM2.5-VL-3B does not fit this workload in one request. LFM2.5-VL-3B has no comparable published API token rate.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. LFM2.5-VL-3B does not fit this workload in one request. LFM2.5-VL-3B has no comparable published API token rate.

    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
2
Inkling only
19
LFM2.5-VL-3B only
8
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, 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
38.3
Supported · #122/152
LFM2.5-VL-3B
Not ranked
Basis
BenchAlign lane · 4 vs 1 public rows
Reading
Not comparable

Coding

Not comparable
Inkling
41.1
Supported · #111/151
LFM2.5-VL-3B
Not ranked
Basis
BenchAlign lane · 6 vs 0 public rows
Reading
Not comparable

Reasoning

Not comparable
Inkling
74.1
Unranked · 2 rankable rows
LFM2.5-VL-3B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Inkling
57.4
Supported · #43/183
LFM2.5-VL-3B
Not ranked
Basis
BenchAlign lane · 6 vs 0 public rows
Reading
Not comparable

Math

Not comparable
Inkling
78.9
Unranked · 1 rankable row
LFM2.5-VL-3B
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Inkling
Not ranked
LFM2.5-VL-3B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Inkling
49.2
#38/48
LFM2.5-VL-3B
Not ranked
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Inkling
85.2
#44/123
LFM2.5-VL-3B
Not ranked
Basis
Provisional lane · 1 vs 1 weighted rows
Reading
Not comparable

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

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

Inkling
$0.00421
Fits in one request
LFM2.5-VL-3B
Self-hosted; infrastructure cost varies
Fits in one request

LFM2.5-VL-3B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Inkling
$0.10754
Fits in one request
LFM2.5-VL-3B
Self-hosted; infrastructure cost varies
Does not fit in one request

LFM2.5-VL-3B does not fit this workload in one request. LFM2.5-VL-3B has no comparable published API token rate.

Cache-heavy agent loop

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

Inkling
$0.159
Fits in one request
LFM2.5-VL-3B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable

LFM2.5-VL-3B does not fit this workload in one request. LFM2.5-VL-3B 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.

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

LFM2.5-VL-3B

No comparable hosted API rate

Liquid AI LFM2.5-VL-3B model card

Documented inputs

Inkling

Not sourced

LFM2.5-VL-3B

Not sourced

Documented outputs

Inkling

Not sourced

LFM2.5-VL-3B

Not sourced

Provider availability

Inkling

Not sourced

LFM2.5-VL-3B

Not sourced

Reasoning profile

Inkling

Hybrid

LFM2.5-VL-3B

Non-Reasoning

Weight access

Inkling

Open Weight

LFM2.5-VL-3B

Open Weight

License

Inkling

Open Weight

LFM2.5-VL-3B

Open Weight

Release date

Inkling

2026-07-15

LFM2.5-VL-3B

2026-08-12

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
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Inkling has the larger documented window (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 evidence29 rows

Agentic

  • Terminal-Bench 2.0

    Inkling63.8%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • BrowseComp

    Inkling77.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • MCP Atlas

    Inkling74.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Inkling47.6%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • BFCL v4

    Inkling—
    LFM2.5-VL-3B32.5%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Inkling77.6%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • SWE-bench Pro

    Inkling54.3%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • Terminal-Bench 2.0

    Inkling63.8%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • FrontierSWE v2

    Inkling4.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • LiveCodeBench (Vals)

    Inkling85.5%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • SWE-bench (Vals)

    Inkling77.6%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

Knowledge

  • GPQA

    Inkling87.9%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • GPQA-D

    Inkling87.9%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • HLE

    Inkling46%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • HLE w/o tools

    Inkling30%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • GPQA Diamond (Vals)

    Inkling87.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • MMLU-Pro (Vals)

    Inkling86.3%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

Math

  • AIME26

    Inkling97.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Inkling73.5%
    Source
    LFM2.5-VL-3B30.5%
    Source

    Inkling leads this result

  • CharXiv

    Inkling82%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • CharXiv w/o tools

    Inkling78.1%
    Source
    LFM2.5-VL-3B—

    Not directly comparable

  • RealWorldQA

    Inkling—
    LFM2.5-VL-3B73.1%
    Source

    Not directly comparable

  • SimpleVQA

    Inkling—
    LFM2.5-VL-3B35.4%
    Source

    Not directly comparable

  • CountBench

    Inkling—
    LFM2.5-VL-3B87.3%
    Source

    Not directly comparable

  • MMMU

    Inkling—
    LFM2.5-VL-3B48.4%
    Source

    Not directly comparable

  • OCRBench V2

    Inkling—
    LFM2.5-VL-3B47.5%
    Source

    Not directly comparable

  • RefCOCO (avg)

    Inkling—
    LFM2.5-VL-3B87.9%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Inkling79.8%
    Source
    LFM2.5-VL-3B25.8%
    Source

    Inkling leads this result

  • IFEval

    Inkling—
    LFM2.5-VL-3B82.3%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Inkling or LFM2.5-VL-3B?

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, Inkling or LFM2.5-VL-3B?

LFM2.5-VL-3B is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Inkling or LFM2.5-VL-3B?

LFM2.5-VL-3B is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Inkling or LFM2.5-VL-3B?

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, Inkling or LFM2.5-VL-3B?

Inkling has the larger documented context window: 1M, compared with 32K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch Inkling vs LFM2.5-VL-3B

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

Read a sample issue

Join 2,000+ readers.