Skip to main content
Radar

Provider changes are easy to miss. Radar watches releases, pricing, deprecations, and incidents at the source.Provider changes are easy to miss.

See Radar
BenchLM
Advertise

Model comparison

GPT-5.6 Luna vs Muse Spark

Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

GPT-5.6 Luna

OpenAI

66.9/100

Estimated · Public rank #23

90% interval 56.4–77.3

Muse Spark

Meta

70.5/100

Supported · Public rank #16

90% interval 61.7–79.2

Muse Spark has the higher public score estimate, 70.47 versus 66.87, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

9 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

    GPT-5.6 Luna

    GPT-5.6 Luna 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
9
GPT-5.6 Luna only
13
Muse Spark only
15
Like-for-like categories
2 / 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.

Reasoning

Like-for-like
GPT-5.6 Luna
59.5
Muse Spark
42.5
Weighted basis
1 vs 1 rows
Reading
GPT-5.6 Luna leads

Math

Like-for-like
GPT-5.6 Luna
73.6
Muse Spark
32.9
Weighted basis
2 vs 2 rows
Reading
GPT-5.6 Luna leads

Agentic

Directional only
GPT-5.6 Luna
84.1
Muse Spark
59.0
Weighted basis
2 vs 1 rows
Reading
Directional only

Coding

Directional only
GPT-5.6 Luna
62.7
Muse Spark
67.8
Weighted basis
1 vs 2 rows
Reading
Directional only

Multimodal

Directional only
GPT-5.6 Luna
78.4
Muse Spark
82.5
Weighted basis
1 vs 2 rows
Reading
Directional only

Knowledge

Not comparable
GPT-5.6 Luna
92.3
Muse Spark
50.4
Weighted basis
1 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.6 Luna
Not measured
Muse Spark
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.6 Luna
Not measured
Muse Spark
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

GPT-5.6 Luna
$0.0008
Fits in one request
Muse Spark
API rate not published
Fits in one request

Muse Spark has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GPT-5.6 Luna
$0.0136
Fits in one request
Muse Spark
API rate not published
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

GPT-5.6 Luna
$0.02
Fits in one request
Muse Spark
API rate not published
Fits in one request
Cached-input rate unavailable

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.

GPT-5.6 Luna

1.05M

OpenAI model catalog

Muse Spark

262K

Cached-input rate

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

GPT-5.6 Luna

$0.02 per 1M cached input tokens

OpenAI pricing

Muse Spark

No comparable hosted API rate

Provider availability

GPT-5.6 Luna

Generally Available · OpenAI Responses API

OpenAI model catalog

Muse Spark

Not sourced

Reasoning profile

GPT-5.6 Luna

Reasoning

Muse Spark

Reasoning

Weight access

GPT-5.6 Luna

Proprietary

Muse Spark

Proprietary

License

GPT-5.6 Luna

Proprietary

Muse Spark

Proprietary

Release date

GPT-5.6 Luna

2026-07-09

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
Muse Spark has the higher public score estimate, 70.47 versus 66.87, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
GPT-5.6 Luna has the larger documented window (1.05M).

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 evidence37 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.6 Luna84.7%
    Source
    Muse Spark59%
    Source

    GPT-5.6 Luna leads this result

  • BrowseComp

    GPT-5.6 Luna83.3%
    Source
    Muse Spark—

    Not directly comparable

  • OSWorld 2.0

    GPT-5.6 Luna45.6%
    Source
    Muse Spark—

    Not directly comparable

  • CyberGym

    GPT-5.6 Luna77.9%
    Source
    Muse Spark43.5%
    Source

    GPT-5.6 Luna leads this result

  • ExploitGym

    GPT-5.6 Luna12.4%
    Source
    Muse Spark—

    Not directly comparable

  • Toolathlon

    GPT-5.6 Luna53.4%
    Source
    Muse Spark—

    Not directly comparable

  • τ²-bench results

    GPT-5.6 Luna—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    GPT-5.6 Luna—
    Muse Spark74.8%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-5.6 Luna—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    GPT-5.6 Luna62.7%
    Source
    Muse Spark52.4%
    Source

    GPT-5.6 Luna leads this result

  • Terminal-Bench 2.0

    GPT-5.6 Luna84.7%
    Source
    Muse Spark—

    Not directly comparable

  • deepSwe

    GPT-5.6 Luna67.2%
    Source
    Muse Spark—

    Not directly comparable

  • FrontierCode 1.1 Extended

    GPT-5.6 Luna55.1%
    Source
    Muse Spark—

    Not directly comparable

  • cursorBench32

    GPT-5.6 Luna61.1%
    Source
    Muse Spark—

    Not directly comparable

  • SWE-bench Verified

    GPT-5.6 Luna—
    Muse Spark77.4%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    GPT-5.6 Luna—
    Muse Spark80.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    GPT-5.6 Luna—
    Muse Spark19.67%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.6 Luna59.5%
    Source
    Muse Spark42.5%
    Source

    GPT-5.6 Luna leads this result

  • ARC-AGI-3

    GPT-5.6 Luna0.2%
    Source
    Muse Spark—

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.6 Luna92.3%
    Source
    Muse Spark—

    Not directly comparable

  • GPQA-D

    GPT-5.6 Luna92.3%
    Source
    Muse Spark89.5%
    Source

    GPT-5.6 Luna leads this result

  • HealthBench Professional

    GPT-5.6 Luna55.7%
    Source
    Muse Spark—

    Not directly comparable

  • HealthBench Hard

    GPT-5.6 Luna32.0%
    Source
    Muse Spark42.8%
    Source

    Muse Spark leads this result

  • HLE

    GPT-5.6 Luna—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    GPT-5.6 Luna—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    GPT-5.6 Luna—
    Muse Spark52.6%
    Source

    Not directly comparable

Math

  • FrontierMath (legacy)

    GPT-5.6 Luna78.6%
    Source
    Muse Spark—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    GPT-5.6 Luna78.600%
    Source
    Muse Spark39.000%
    Source

    GPT-5.6 Luna leads this result

  • FrontierMath v2 (Tier 4)

    GPT-5.6 Luna58.500%
    Source
    Muse Spark14.600%
    Source

    GPT-5.6 Luna leads this result

Multimodal

  • MMMU-Pro

    GPT-5.6 Luna78.4%
    Source
    Muse Spark80.4%
    Source

    Muse Spark leads this result

  • MMMU-Pro w/ Python

    GPT-5.6 Luna79.5%
    Source
    Muse Spark—

    Not directly comparable

  • CharXiv

    GPT-5.6 Luna—
    Muse Spark86.4%
    Source

    Not directly comparable

  • ERQA

    GPT-5.6 Luna—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    GPT-5.6 Luna—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    GPT-5.6 Luna—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    GPT-5.6 Luna—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    GPT-5.6 Luna—
    Muse Spark78.4%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.6 Luna or Muse Spark?

Muse Spark has the higher public score estimate, 70.47 versus 66.87, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-5.6 Luna or Muse Spark?

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, GPT-5.6 Luna or Muse Spark?

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, GPT-5.6 Luna 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, GPT-5.6 Luna or Muse Spark?

GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 10, 2026

Watch GPT-5.6 Luna 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.