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

70.6/100

Supported · Public rank #17

90% interval 61.0–80.2

Muse Spark vs Muse Spark 1.1

Updated August 22, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.

Model B
Muse Spark 1.1

Meta

76.7/100

Supported · Public rank #7

90% interval 72.6–80.9

Decision reading

Muse Spark 1.1 has the higher public score estimate, 76.74 versus 70.6, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 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 1.1

    Muse Spark 1.1 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

  • Agentic work

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

    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
7
Muse Spark only
17
Muse Spark 1.1 only
14
Like-for-like categories
1 / 8

3 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.

Knowledge

Like-for-like
Muse Spark
50.4
Muse Spark 1.1
62.1
Weighted basis
1 vs 1 rows
Reading
Muse Spark 1.1 leads

Agentic

Directional only
Muse Spark
59.0
Muse Spark 1.1
80.4
Weighted basis
1 vs 2 rows
Reading
Directional only

Coding

Directional only
Muse Spark
67.8
Muse Spark 1.1
61.5
Weighted basis
2 vs 1 rows
Reading
Directional only

Multimodal

Directional only
Muse Spark
82.5
Muse Spark 1.1
88.4
Weighted basis
2 vs 1 rows
Reading
Directional only

Reasoning

Not comparable
Muse Spark
42.5
Muse Spark 1.1
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Muse Spark
32.9
Muse Spark 1.1
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Muse Spark
Not measured
Muse Spark 1.1
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Muse Spark
Not measured
Muse Spark 1.1
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
Muse Spark 1.1
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate. Muse Spark 1.1 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
Muse Spark 1.1
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate. Muse Spark 1.1 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
Muse Spark 1.1
API rate not published
Fits in one request
Cached-input rate unavailable

Muse Spark has no comparable published API token rate. Muse Spark 1.1 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

Muse Spark 1.1

1M

API model ID

Muse Spark

Not sourced

Muse Spark 1.1

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

Muse Spark 1.1

No comparable hosted API rate

Documented inputs

Muse Spark

Not sourced

Muse Spark 1.1

Not sourced

Documented outputs

Muse Spark

Not sourced

Muse Spark 1.1

Not sourced

Provider availability

Muse Spark

Not sourced

Muse Spark 1.1

Not sourced

Reasoning profile

Muse Spark

Reasoning

Muse Spark 1.1

Reasoning

Weight access

Muse Spark

Proprietary

Muse Spark 1.1

Proprietary

License

Muse Spark

Proprietary

Muse Spark 1.1

Proprietary

Release date

Muse Spark

2026-04-08

Muse Spark 1.1

2026-07-09

If you are considering the documented upgrade path
Deployment change
Both entries list Meta as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Muse Spark 1.1 has the higher public score estimate, 76.74 versus 70.6, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Muse Spark 1.1 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 evidence38 rows

Agentic

  • Terminal-Bench 2.0

    Muse Spark59%
    Source
    Muse Spark 1.180%
    Source

    Muse Spark 1.1 leads this result

  • τ²-bench results

    Muse Spark91.5%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • DeepSearchQA

    Muse Spark74.8%
    Source
    Muse Spark 1.184.9%
    Source

    Muse Spark 1.1 leads this result

  • CyberGym

    Muse Spark43.5%
    Source
    Muse Spark 1.159.0%
    Source

    Muse Spark 1.1 leads this result

  • Claw-Eval

    Muse Spark63.8%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MCP Atlas

    Muse Spark—
    Muse Spark 1.188.1%
    Source

    Not directly comparable

  • Toolathlon

    Muse Spark—
    Muse Spark 1.175.6%
    Source

    Not directly comparable

  • OSWorld-Verified

    Muse Spark—
    Muse Spark 1.180.8%
    Source

    Not directly comparable

  • WebArena-Verified

    Muse Spark—
    Muse Spark 1.169%
    Source

    Not directly comparable

  • Finance Agent v2

    Muse Spark—
    Muse Spark 1.157.2%
    Source

    Not directly comparable

  • deepSwe

    Muse Spark—
    Muse Spark 1.153.3%
    Source

    Not directly comparable

  • OSWorld 2.0

    Muse Spark—
    Muse Spark 1.114.2%
    Source

    Not directly comparable

  • JobBench

    Muse Spark—
    Muse Spark 1.154.7%
    Source

    Not directly comparable

  • Cybench

    Muse Spark—
    Muse Spark 1.192.9%
    Source

    Not directly comparable

  • ExploitGym

    Muse Spark—
    Muse Spark 1.10.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Muse Spark77.4%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • SWE-bench Pro

    Muse Spark52.4%
    Source
    Muse Spark 1.161.5%
    Source

    Muse Spark 1.1 leads this result

  • LiveCodeBench Pro

    Muse Spark80.0%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • Vibe Code Bench

    Muse Spark19.67%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • Terminal-Bench 2.0

    Muse Spark—
    Muse Spark 1.180.0%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Muse Spark42.5%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MRCR 1M

    Muse Spark—
    Muse Spark 1.154.1%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Muse Spark89.5%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • HLE

    Muse Spark50.4%
    Source
    Muse Spark 1.162.1%
    Source

    Muse Spark 1.1 leads this result

  • HLE w/o tools

    Muse Spark42.8%
    Source
    Muse Spark 1.152.2%
    Source

    Muse Spark 1.1 leads this result

  • HealthBench Hard

    Muse Spark42.8%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MedXpertQA (Text)

    Muse Spark52.6%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • HealthBench Professional

    Muse Spark—
    Muse Spark 1.159.3%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Muse Spark39.000%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Muse Spark14.600%
    Source
    Muse Spark 1.1—

    Not directly comparable

Multimodal

  • CharXiv

    Muse Spark86.4%
    Source
    Muse Spark 1.188.4%
    Source

    Muse Spark 1.1 leads this result

  • MMMU-Pro

    Muse Spark80.4%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • ERQA

    Muse Spark64.7%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • SimpleVQA

    Muse Spark71.3%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • ScreenSpot Pro

    Muse Spark84.1%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • ZeroBench

    Muse Spark33.0%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MedXpertQA (MM)

    Muse Spark78.4%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • BabyVision

    Muse Spark—
    Muse Spark 1.176.3%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Muse Spark or Muse Spark 1.1?

Muse Spark 1.1 has the higher public score estimate, 76.74 versus 70.6, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Muse Spark or Muse Spark 1.1?

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 Muse Spark 1.1?

The current agentic tasks 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 costs less, Muse Spark or Muse Spark 1.1?

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 Muse Spark 1.1?

Muse Spark 1.1 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 22, 2026

Watch Muse Spark vs Muse Spark 1.1

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

Read a sample issue

Join 2,000+ readers.