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
Muse Spark

Meta

70.7/100

Supported · Public rank #17

90% interval 61.5–79.8

Muse Spark vs Sakana Fugu

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

Model B
Sakana Fugu

Sakana AI

—

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.

6 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.

  • Agentic work

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

    Sakana Fugu

    Sakana Fugu leads on the same 1 weighted benchmark row.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    Sakana Fugu

    Sakana Fugu 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

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

    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

    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
6
Muse Spark only
18
Sakana Fugu only
5
Like-for-like categories
1 / 8

2 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

Like-for-like
Muse Spark
59.0
Sakana Fugu
80.2
Weighted basis
1 vs 1 rows
Reading
Sakana Fugu leads

Coding

Directional only
Muse Spark
67.8
Sakana Fugu
59.7
Weighted basis
2 vs 2 rows
Reading
Directional only

Multimodal

Directional only
Muse Spark
82.5
Sakana Fugu
85.1
Weighted basis
2 vs 1 rows
Reading
Directional only

Reasoning

Not comparable
Muse Spark
42.5
Sakana Fugu
86.6
Weighted basis
1 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Muse Spark
50.4
Sakana Fugu
95.5
Weighted basis
1 vs 1 rows
Reading
Not comparable

Math

Not comparable
Muse Spark
32.9
Sakana Fugu
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Muse Spark
Not measured
Sakana Fugu
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Muse Spark
Not measured
Sakana Fugu
Not measured
Weighted basis
0 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.

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

Muse Spark
API rate not published
Fits in one request
Sakana Fugu
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate. Sakana Fugu has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Muse Spark
API rate not published
Fits in one request
Sakana Fugu
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate. Sakana Fugu has no comparable published API token rate.

Cache-heavy agent loop

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

Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable
Sakana Fugu
API rate not published
Fits in one request
Cached-input rate unavailable

Muse Spark has no comparable published API token rate. Sakana Fugu 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.

Muse Spark

262K

Sakana Fugu

1M

API model ID

Muse Spark

Not sourced

Sakana Fugu

Not sourced

Cached-input rate

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

Muse Spark

No comparable hosted API rate

Sakana Fugu

No comparable hosted API rate

Documented inputs

Muse Spark

Not sourced

Sakana Fugu

Not sourced

Documented outputs

Muse Spark

Not sourced

Sakana Fugu

Not sourced

Provider availability

Muse Spark

Not sourced

Sakana Fugu

Not sourced

Reasoning profile

Muse Spark

Reasoning

Sakana Fugu

Reasoning

Weight access

Muse Spark

Proprietary

Sakana Fugu

Proprietary

License

Muse Spark

Proprietary

Sakana Fugu

Proprietary

Release date

Muse Spark

2026-04-08

Sakana Fugu

2026-06-22

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
Sakana Fugu 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

    Muse Spark59%
    Source
    Sakana Fugu80.2%
    Source

    Sakana Fugu leads this result

  • τ²-bench results

    Muse Spark91.5%
    Source
    Sakana Fugu—

    Not directly comparable

  • DeepSearchQA

    Muse Spark74.8%
    Source
    Sakana Fugu—

    Not directly comparable

  • CyberGym

    Muse Spark43.5%
    Source
    Sakana Fugu—

    Not directly comparable

  • Claw-Eval

    Muse Spark63.8%
    Source
    Sakana Fugu—

    Not directly comparable

Coding

  • SWE-bench Verified

    Muse Spark77.4%
    Source
    Sakana Fugu—

    Not directly comparable

  • SWE-bench Pro

    Muse Spark52.4%
    Source
    Sakana Fugu59%
    Source

    Sakana Fugu leads this result

  • LiveCodeBench Pro

    Muse Spark80.0%
    Source
    Sakana Fugu87.8%
    Source

    Sakana Fugu leads this result

  • Vibe Code Bench

    Muse Spark19.67%
    Source
    Sakana Fugu—

    Not directly comparable

  • Terminal-Bench 2.0

    Muse Spark—
    Sakana Fugu80.2%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Muse Spark—
    Sakana Fugu92.9%
    Source

    Not directly comparable

  • SciCode

    Muse Spark—
    Sakana Fugu60.1%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Muse Spark42.5%
    Source
    Sakana Fugu—

    Not directly comparable

  • MRCRv2

    Muse Spark—
    Sakana Fugu86.6%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Muse Spark89.5%
    Source
    Sakana Fugu95.5%
    Source

    Sakana Fugu leads this result

  • HLE

    Muse Spark50.4%
    Source
    Sakana Fugu—

    Not directly comparable

  • HLE w/o tools

    Muse Spark42.8%
    Source
    Sakana Fugu47.2%
    Source

    Sakana Fugu leads this result

  • HealthBench Hard

    Muse Spark42.8%
    Source
    Sakana Fugu—

    Not directly comparable

  • MedXpertQA (Text)

    Muse Spark52.6%
    Source
    Sakana Fugu—

    Not directly comparable

  • GPQA

    Muse Spark—
    Sakana Fugu95.5%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Muse Spark39.000%
    Source
    Sakana Fugu—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Muse Spark14.600%
    Source
    Sakana Fugu—

    Not directly comparable

Multimodal

  • CharXiv

    Muse Spark86.4%
    Source
    Sakana Fugu85.1%
    Source

    Muse Spark leads this result

  • MMMU-Pro

    Muse Spark80.4%
    Source
    Sakana Fugu—

    Not directly comparable

  • ERQA

    Muse Spark64.7%
    Source
    Sakana Fugu—

    Not directly comparable

  • SimpleVQA

    Muse Spark71.3%
    Source
    Sakana Fugu—

    Not directly comparable

  • ScreenSpot Pro

    Muse Spark84.1%
    Source
    Sakana Fugu—

    Not directly comparable

  • ZeroBench

    Muse Spark33.0%
    Source
    Sakana Fugu—

    Not directly comparable

  • MedXpertQA (MM)

    Muse Spark78.4%
    Source
    Sakana Fugu—

    Not directly comparable

Frequently asked questions

Which is better, Muse Spark or Sakana Fugu?

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, Muse Spark or Sakana Fugu?

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, Muse Spark or Sakana Fugu?

Sakana Fugu leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.

Which costs less, Muse Spark or Sakana Fugu?

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, Muse Spark or Sakana Fugu?

Sakana Fugu has the larger documented context window: 1M, compared with 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 13, 2026

Watch Muse Spark vs Sakana Fugu

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

Read a sample issue

Join 2,000+ readers.