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
BenchLM
Meta logo
Model A
Muse Spark 1.1

Meta

76.7/100

Supported · Public rank #10

90% interval 71.9–81.5

Muse Spark 1.1 vs Muse Spark 1.3

Updated September 2, 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.

Meta logo
Model B
Muse Spark 1.3

Meta

—

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.

3 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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

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

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • 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
3
Muse Spark 1.1 only
18
Muse Spark 1.3 only
7
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
Muse Spark 1.1
80.4
Muse Spark 1.3
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Muse Spark 1.1
61.5
Muse Spark 1.3
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Muse Spark 1.1
Not measured
Muse Spark 1.3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Muse Spark 1.1
62.1
Muse Spark 1.3
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Muse Spark 1.1
Not measured
Muse Spark 1.3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Muse Spark 1.1
Not measured
Muse Spark 1.3
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Muse Spark 1.1
88.4
Muse Spark 1.3
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Muse Spark 1.1
Not measured
Muse Spark 1.3
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.

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 1.1
API rate not published
Fits in one request
Muse Spark 1.3
$0.00338
Fits in one request

Muse Spark 1.1 has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Muse Spark 1.1
API rate not published
Fits in one request
Muse Spark 1.3
$0.07525
Fits in one request

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 1.1
API rate not published
Fits in one request
Cached-input rate unavailable
Muse Spark 1.3
$0.0975
Fits in one request

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.

Cached-input rate

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

Muse Spark 1.1

No comparable hosted API rate

Muse Spark 1.3

$0.15 per 1M cached input tokens

Meta: Muse Spark 1.3 model page

Reasoning profile

Muse Spark 1.1

Reasoning

Muse Spark 1.3

Reasoning

Weight access

Muse Spark 1.1

Proprietary

Muse Spark 1.3

Proprietary

License

Muse Spark 1.1

Proprietary

Muse Spark 1.3

Proprietary

Release date

Muse Spark 1.1

2026-07-09

Muse Spark 1.3

2026-09-02

If you are choosing between sibling variants
Deployment change
Both entries list Meta as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
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
Both models list 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 evidence28 rows

Agentic

  • Terminal-Bench 2.0

    Muse Spark 1.180%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • MCP Atlas

    Muse Spark 1.188.1%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • Toolathlon

    Muse Spark 1.175.6%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • OSWorld-Verified

    Muse Spark 1.180.8%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • WebArena-Verified

    Muse Spark 1.169%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • DeepSearchQA

    Muse Spark 1.184.9%
    Source
    Muse Spark 1.389.4%
    Source

    Muse Spark 1.3 leads this result

  • CyberGym

    Muse Spark 1.159.0%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • Finance Agent v2

    Muse Spark 1.157.2%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • deepSwe

    Muse Spark 1.153.3%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • OSWorld 2.0

    Muse Spark 1.114.2%
    Source
    Muse Spark 1.366.9%
    Source

    Muse Spark 1.3 leads this result

  • JobBench

    Muse Spark 1.154.7%
    Source
    Muse Spark 1.364.9%
    Source

    Muse Spark 1.3 leads this result

  • Cybench

    Muse Spark 1.192.9%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • ExploitGym

    Muse Spark 1.10.8%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • Terminal-Bench 2.1

    Muse Spark 1.1—
    Muse Spark 1.388.8%
    Source

    Not directly comparable

  • AutomationBench

    Muse Spark 1.1—
    Muse Spark 1.349.4%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.0

    Muse Spark 1.180.0%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • SWE-bench Pro

    Muse Spark 1.161.5%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • Terminal-Bench 2.1

    Muse Spark 1.1—
    Muse Spark 1.388.8%
    Source

    Not directly comparable

  • deepSwe

    Muse Spark 1.1—
    Muse Spark 1.375.4%
    Source

    Not directly comparable

  • SWE-Atlas Codebase QnA

    Muse Spark 1.1—
    Muse Spark 1.359.4%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    Muse Spark 1.154.1%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • MRCR v2 256K-512K

    Muse Spark 1.1—
    Muse Spark 1.398.5%
    Source

    Not directly comparable

  • MRCR v2 512K-1M

    Muse Spark 1.1—
    Muse Spark 1.398.1%
    Source

    Not directly comparable

Knowledge

  • HLE

    Muse Spark 1.162.1%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • HLE w/o tools

    Muse Spark 1.152.2%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • HealthBench Professional

    Muse Spark 1.159.3%
    Source
    Muse Spark 1.3—

    Not directly comparable

Multimodal

  • CharXiv

    Muse Spark 1.188.4%
    Source
    Muse Spark 1.3—

    Not directly comparable

  • BabyVision

    Muse Spark 1.176.3%
    Source
    Muse Spark 1.3—

    Not directly comparable

Frequently asked questions

Which is better, Muse Spark 1.1 or Muse Spark 1.3?

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 1.1 or Muse Spark 1.3?

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, Muse Spark 1.1 or Muse Spark 1.3?

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, Muse Spark 1.1 or Muse Spark 1.3?

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 1.1 or Muse Spark 1.3?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 2, 2026

Watch Muse Spark 1.1 vs Muse Spark 1.3

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

Read a sample issue

Join 2,000+ readers.