Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Model A
LFM2.5-230M

LiquidAI

—

Evidence status unavailable

90% interval unavailable

LFM2.5-230M vs Muse Spark

Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Muse Spark

Meta

70.5/100

Supported · Public rank #17

90% interval 61.4–79.7

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.

1 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.

  • Long documents

    Prompts that approach the documented context limit

    Muse Spark

    Muse Spark 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

    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

  • 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. LFM2.5-230M does not fit this workload in one request. LFM2.5-230M has no comparable published API token rate. Muse Spark 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. LFM2.5-230M does not fit this workload in one request. LFM2.5-230M has no comparable published API token rate. Muse Spark 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
1
LFM2.5-230M only
5
Muse Spark only
23
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
LFM2.5-230M
Not measured
Muse Spark
59.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Coding

Not comparable
LFM2.5-230M
Not measured
Muse Spark
67.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
LFM2.5-230M
Not measured
Muse Spark
42.5
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
LFM2.5-230M
21.2
Muse Spark
50.4
Weighted basis
2 vs 1 rows
Reading
Not comparable

Math

Not comparable
LFM2.5-230M
Not measured
Muse Spark
32.9
Weighted basis
0 vs 2 rows
Reading
Not comparable

Multilingual

Not comparable
LFM2.5-230M
Not measured
Muse Spark
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
LFM2.5-230M
Not measured
Muse Spark
82.5
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
LFM2.5-230M
50.1
Muse Spark
Not measured
Weighted basis
2 vs 0 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

LFM2.5-230M
Self-hosted; infrastructure cost varies
Fits in one request
Muse Spark
API rate not published
Fits in one request

LFM2.5-230M has no comparable published API token rate. Muse Spark has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

LFM2.5-230M
Self-hosted; infrastructure cost varies
Does not fit in one request
Muse Spark
API rate not published
Fits in one request

LFM2.5-230M does not fit this workload in one request. LFM2.5-230M has no comparable published API token rate. Muse Spark has no comparable published API token rate.

Cache-heavy agent loop

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

LFM2.5-230M
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable
Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable

LFM2.5-230M does not fit this workload in one request. LFM2.5-230M has no comparable published API token rate. Muse Spark 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.

LFM2.5-230M

32K

Muse Spark

262K

API model ID

LFM2.5-230M

Not sourced

Muse Spark

Not sourced

Cached-input rate

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

LFM2.5-230M

No comparable hosted API rate

Muse Spark

No comparable hosted API rate

Documented inputs

LFM2.5-230M

Not sourced

Muse Spark

Not sourced

Documented outputs

LFM2.5-230M

Not sourced

Muse Spark

Not sourced

Provider availability

LFM2.5-230M

Not sourced

Muse Spark

Not sourced

Reasoning profile

LFM2.5-230M

Non-Reasoning

Muse Spark

Reasoning

Weight access

LFM2.5-230M

Open Weight

Muse Spark

Proprietary

License

LFM2.5-230M

Open Weight

Muse Spark

Proprietary

Release date

LFM2.5-230M

2026-06-25

Muse Spark

2026-04-08

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
Muse Spark has the larger documented window (262K).

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

  • BFCL v4

    LFM2.5-230M21.0%
    Source
    Muse Spark—

    Not directly comparable

  • Terminal-Bench 2.0

    LFM2.5-230M—
    Muse Spark59%
    Source

    Not directly comparable

  • τ²-bench results

    LFM2.5-230M—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    LFM2.5-230M—
    Muse Spark74.8%
    Source

    Not directly comparable

  • CyberGym

    LFM2.5-230M—
    Muse Spark43.5%
    Source

    Not directly comparable

  • Claw-Eval

    LFM2.5-230M—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    LFM2.5-230M—
    Muse Spark77.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    LFM2.5-230M—
    Muse Spark52.4%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    LFM2.5-230M—
    Muse Spark80.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    LFM2.5-230M—
    Muse Spark19.67%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    LFM2.5-230M—
    Muse Spark42.5%
    Source

    Not directly comparable

Knowledge

  • GPQA

    LFM2.5-230M25.4%
    Source
    Muse Spark—

    Not directly comparable

  • GPQA-D

    LFM2.5-230M25.4%
    Source
    Muse Spark89.5%
    Source

    Muse Spark leads this result

  • MMLU-Pro

    LFM2.5-230M20.3%
    Source
    Muse Spark—

    Not directly comparable

  • HLE

    LFM2.5-230M—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    LFM2.5-230M—
    Muse Spark42.8%
    Source

    Not directly comparable

  • HealthBench Hard

    LFM2.5-230M—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    LFM2.5-230M—
    Muse Spark52.6%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    LFM2.5-230M—
    Muse Spark39.000%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    LFM2.5-230M—
    Muse Spark14.600%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    LFM2.5-230M—
    Muse Spark86.4%
    Source

    Not directly comparable

  • MMMU-Pro

    LFM2.5-230M—
    Muse Spark80.4%
    Source

    Not directly comparable

  • ERQA

    LFM2.5-230M—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    LFM2.5-230M—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    LFM2.5-230M—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    LFM2.5-230M—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    LFM2.5-230M—
    Muse Spark78.4%
    Source

    Not directly comparable

Instruction following

  • IFEval

    LFM2.5-230M71.7%
    Source
    Muse Spark—

    Not directly comparable

  • IFBench

    LFM2.5-230M38.4%
    Source
    Muse Spark—

    Not directly comparable

Frequently asked questions

Which is better, LFM2.5-230M or Muse Spark?

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, LFM2.5-230M or Muse Spark?

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, LFM2.5-230M or Muse Spark?

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, LFM2.5-230M or Muse Spark?

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, LFM2.5-230M or Muse Spark?

Muse Spark has the larger documented context window: 262K, compared with 32K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 13, 2026

Watch LFM2.5-230M vs Muse Spark

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

Read a sample issue

Join 2,000+ readers.