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.

See the free Radar Brief
Meta logo
Model A
Muse Spark

Meta

68.39/100

Supported · Public rank #30

90% interval 60.076.8

Muse Spark vs Fugu Cyber

Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Sakana AI logo
Model B
Fugu Cyber

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.

1 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

    Fugu Cyber

    Fugu Cyber 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

    Fugu Cyber 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

    Fugu Cyber 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

    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
1
Muse Spark only
23
Fugu Cyber only
1
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
Muse Spark
58.8
Supported · #31/151
Fugu Cyber
Not ranked
Basis
BenchAlign lane · 5 vs 2 public rows
Reading
Not comparable

Coding

Not comparable
Muse Spark
59.2
Supported · #28/183
Fugu Cyber
Not ranked
Basis
BenchAlign lane · 4 vs 0 public rows
Reading
Not comparable

Reasoning

Not comparable
Muse Spark
45.9
Unranked · 3 rankable rows
Fugu Cyber
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Muse Spark
65.6
Supported · #23/181
Fugu Cyber
Not ranked
Basis
BenchAlign lane · 5 vs 0 public rows
Reading
Not comparable

Math

Not comparable
Muse Spark
55.3
Unranked · 2 rankable rows
Fugu Cyber
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Muse Spark
Not ranked
Fugu Cyber
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Muse Spark
76.8
#14/48
Fugu Cyber
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Muse Spark
92.9
#8/120
Fugu Cyber
Not ranked
Basis
Provisional lane · 0 vs 0 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.

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

Muse Spark
API rate not published
Fits in one request
Fugu Cyber
$0.024
Fits in one request

Muse Spark 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
Fugu Cyber
$0.408
Fits in one request

Muse Spark 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
Fugu Cyber
$0.6
Fits in one request

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.

Muse Spark

262K

Fugu Cyber

1M

API model ID

Muse Spark

Not sourced

Fugu Cyber

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

Fugu Cyber

$0.6 per 1M cached input tokens

Documented inputs

Muse Spark

Not sourced

Fugu Cyber

Not sourced

Documented outputs

Muse Spark

Not sourced

Fugu Cyber

Not sourced

Provider availability

Muse Spark

Not sourced

Fugu Cyber

Not sourced

Reasoning profile

Muse Spark

Reasoning

Fugu Cyber

Reasoning

Weight access

Muse Spark

Proprietary

Fugu Cyber

Proprietary

License

Muse Spark

Proprietary

Fugu Cyber

Proprietary

Release date

Muse Spark

2026-04-08

Fugu Cyber

2026-07-21

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
Fugu Cyber 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 evidence25 rows

Agentic

  • Terminal-Bench 2.0

    Muse Spark59%
    Source
    Fugu Cyber

    Not directly comparable

  • τ²-bench results

    Muse Spark91.5%
    Source
    Fugu Cyber

    Not directly comparable

  • DeepSearchQA

    Muse Spark74.8%
    Source
    Fugu Cyber

    Not directly comparable

  • CyberGym

    Muse Spark43.5%
    Source
    Fugu Cyber86.9%
    Source

    Fugu Cyber leads this result

  • Claw-Eval

    Muse Spark63.8%
    Source
    Fugu Cyber

    Not directly comparable

  • CTI-REALM

    Muse Spark
    Fugu Cyber72.1%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Muse Spark77.4%
    Source
    Fugu Cyber

    Not directly comparable

  • SWE-bench Pro

    Muse Spark52.4%
    Source
    Fugu Cyber

    Not directly comparable

  • LiveCodeBench Pro

    Muse Spark80.0%
    Source
    Fugu Cyber

    Not directly comparable

  • Vibe Code Bench

    Muse Spark19.67%
    Source
    Fugu Cyber

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Muse Spark42.5%
    Source
    Fugu Cyber

    Not directly comparable

Knowledge

  • GPQA-D

    Muse Spark89.5%
    Source
    Fugu Cyber

    Not directly comparable

  • HLE

    Muse Spark50.4%
    Source
    Fugu Cyber

    Not directly comparable

  • HLE w/o tools

    Muse Spark42.8%
    Source
    Fugu Cyber

    Not directly comparable

  • HealthBench Hard

    Muse Spark42.8%
    Source
    Fugu Cyber

    Not directly comparable

  • MedXpertQA (Text)

    Muse Spark52.6%
    Source
    Fugu Cyber

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Muse Spark39.000%
    Source
    Fugu Cyber

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Muse Spark14.600%
    Source
    Fugu Cyber

    Not directly comparable

Multimodal

  • CharXiv

    Muse Spark86.4%
    Source
    Fugu Cyber

    Not directly comparable

  • MMMU-Pro

    Muse Spark80.4%
    Source
    Fugu Cyber

    Not directly comparable

  • ERQA

    Muse Spark64.7%
    Source
    Fugu Cyber

    Not directly comparable

  • SimpleVQA

    Muse Spark71.3%
    Source
    Fugu Cyber

    Not directly comparable

  • ScreenSpot Pro

    Muse Spark84.1%
    Source
    Fugu Cyber

    Not directly comparable

  • ZeroBench

    Muse Spark33.0%
    Source
    Fugu Cyber

    Not directly comparable

  • MedXpertQA (MM)

    Muse Spark78.4%
    Source
    Fugu Cyber

    Not directly comparable

Frequently asked questions

Which is better, Muse Spark or Fugu Cyber?

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 Fugu Cyber?

Fugu Cyber is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Muse Spark or Fugu Cyber?

Fugu Cyber is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Muse Spark or Fugu Cyber?

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 Fugu Cyber?

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

Related comparisons

Last updated September 4, 2026

Watch Muse Spark vs Fugu Cyber

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

Read a sample issue

Join 2,000+ readers.