Skip to main content
BenchLM
Data

GPT-6 Luna vs Muse Ember

Updated November 9, 2026. Rank says GPT-6 Luna is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

GPT-6 Luna has the higher public point estimate, 62.38 versus 56.24. Their conditional score ranges overlap. These ranges do not establish rank confidence. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
OpenAI logo
GPT-6 Luna

OpenAI

62.38/100

Supported · Public rank #44

90% interval 51.6–73.1

Model B
Meta logo
Muse Ember

Meta

56.24/100

Estimated · Public rank #64

Conditional range 41.9–70.6

Shared results
2
GPT-6 Luna only
24
Muse Ember only
2
Like-for-like categories
0 / 8
Supported: GPT-6 Luna · Estimated: Muse Ember. Conditional ranges do not establish rank confidence.How the comparison works

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-6 Luna

    GPT-6 Luna has the larger documented context window.

    Confidence: documented

  • Cache-heavy agent loop cost

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

    Muse Ember

    Muse Ember has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Muse Ember 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

    Muse Ember 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

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

51.7GPT-6 Luna—Muse Ember

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

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.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, 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
GPT-6 Luna
53.8
Estimated · #47/132
Muse Ember
Not ranked
Basis
BenchAlign v5.8 lane · 7 vs 3 public rows
Reading
Not comparable

Coding

Not comparable
GPT-6 Luna
51.7
Supported · #42/158
Muse Ember
Not ranked
Basis
BenchAlign v5.8 lane · 3 vs 0 public rows
Reading
Not comparable

Reasoning

Not comparable
GPT-6 Luna
54.4
Supported · #46/157
Muse Ember
Not ranked
Basis
BenchAlign v5.8 lane · 5 vs 0 public rows
Reading
Not comparable

Multimodal

Not comparable
GPT-6 Luna
63.8
Supported · #29/67
Muse Ember
Not ranked
Basis
BenchAlign v5.8 lane · 4 vs 1 public rows
Reading
Not comparable

Knowledge

Not comparable
GPT-6 Luna
62.2
Supported · #42/179
Muse Ember
Not ranked
Basis
BenchAlign v5.8 lane · 5 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
GPT-6 Luna
Not ranked
Muse Ember
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-6 Luna
Not ranked
Muse Ember
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-6 Luna
80.2
Unranked · 2 rankable rows
Muse Ember
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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-6 Luna
$0.00035
Fits in one request
Muse Ember
$0.00035
Fits in one request

Modeled costs are equal

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-6 Luna
$0.0065
Fits in one request
Muse Ember
$0.0065
Fits in one request

Modeled costs are equal

Costs use the listed standard API rates.

Cache-heavy agent loop

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

GPT-6 Luna
$0.009
Fits in one request
Muse Ember
$0.0078
Fits in one request

Muse Ember has the lower modeled cost

Costs use the listed standard API rates.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Provider availability

GPT-6 Luna

Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex

OpenAI GPT-6 Sol and Luna launch

Muse Ember

Not sourced

Reasoning profile

GPT-6 Luna

Reasoning

Muse Ember

Reasoning

Weight access

GPT-6 Luna

Proprietary

Muse Ember

Proprietary

License

GPT-6 Luna

Proprietary

Muse Ember

Proprietary

Release date

GPT-6 Luna

2026-09-22

Muse Ember

2026-11-09

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
GPT-6 Luna has the higher public point estimate, 62.38 versus 56.24. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.0065 vs $0.0065. Cache-heavy agent loop: $0.009 vs $0.0078.
Context tradeoff
GPT-6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-6 Luna or Muse Ember?

GPT-6 Luna has the higher public point estimate, 62.38 versus 56.24. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-6 Luna or Muse Ember?

Muse Ember is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, GPT-6 Luna or Muse Ember?

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

Which costs less, GPT-6 Luna or Muse Ember?

For the stated presets, chat costs $0.00035 on GPT-6 Luna and $0.00035 on Muse Ember; repository review costs $0.0065 and $0.0065; the cache-heavy agent loop costs $0.009 and $0.0078. Costs use the listed standard API rates.

Which has the larger context window, GPT-6 Luna or Muse Ember?

GPT-6 Luna has the larger documented context window: 1.05M, compared with 1M.

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 4.1

    GPT-6 Luna15.20%
    Source
    Muse Ember—

    Not directly comparable

  • Agents' Last Exam (Linux)

    Shared source
    GPT-6 Luna57.1%
    Muse Ember61.6%

    Muse Ember leads this result

  • ExploitGym

    GPT-6 Luna11.6%
    Source
    Muse Ember—

    Not directly comparable

  • Hermes Index

    GPT-6 Luna33.9%
    Source
    Muse Ember—

    Not directly comparable

  • Hermes Bench

    GPT-6 Luna70.5%
    Source
    Muse Ember—

    Not directly comparable

  • MazeBench

    GPT-6 Luna0%
    Source
    Muse Ember—

    Not directly comparable

  • OSWorld 2.1 Offline

    GPT-6 Luna48.9%
    Source
    Muse Ember—

    Not directly comparable

  • Terminal-Bench 4.0

    GPT-6 Luna—
    Muse Ember40.90%
    Source

    Not directly comparable

  • OSWorld 2.1

    GPT-6 Luna—
    Muse Ember69.5%
    Source

    Not directly comparable

Coding

  • DeepSWE

    GPT-6 Luna66.6%
    Source
    Muse Ember—

    Not directly comparable

  • Bug Hunt Bench

    GPT-6 Luna18.3 fixes
    Source
    Muse Ember—

    Not directly comparable

  • FrontierCode 2.0

    GPT-6 Luna21.9%
    Source
    Muse Ember—

    Not directly comparable

Reasoning

  • BioBasicsBench

    GPT-6 Luna37.6%
    Source
    Muse Ember—

    Not directly comparable

  • ARC-AGI-1

    GPT-6 Luna86.67%
    Source
    Muse Ember—

    Not directly comparable

  • ARC-AGI-2

    GPT-6 Luna59.3%
    Source
    Muse Ember—

    Not directly comparable

  • ARC-AGI-3

    GPT-6 Luna0.1%
    Source
    Muse Ember—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    GPT-6 Luna0.59%
    Source
    Muse Ember—

    Not directly comparable

Multimodal

  • PerceptionBench (tools)

    Shared source
    GPT-6 Luna62.8%
    Muse Ember80.6%

    Muse Ember leads this result

  • ExtractBench Pro

    GPT-6 Luna0%
    Source
    Muse Ember—

    Not directly comparable

  • ExtractBench (LlamaIndex)

    GPT-6 Luna91.01%
    Source
    Muse Ember—

    Not directly comparable

  • ParseBench

    GPT-6 Luna64.13%
    Source
    Muse Ember—

    Not directly comparable

Knowledge

  • HealthBench (raw)

    GPT-6 Luna50.0%
    Source
    Muse Ember—

    Not directly comparable

  • HealthBench (length-adjusted)

    GPT-6 Luna54.5%
    Source
    Muse Ember—

    Not directly comparable

  • HealthBench Professional

    GPT-6 Luna60.8%
    Source
    Muse Ember—

    Not directly comparable

  • HealthBench Professional (raw)

    GPT-6 Luna61.2%
    Source
    Muse Ember—

    Not directly comparable

  • HealthBench Hard

    GPT-6 Luna31.4%
    Source
    Muse Ember—

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    GPT-6 Luna78.947%
    Source
    Muse Ember—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GPT-6 Luna56.098%
    Source
    Muse Ember—

    Not directly comparable

28 public results · 2 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch GPT-6 Luna vs Muse Ember

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

Read a sample issue

Join 6,100+ subscribers.

Last updated November 9, 2026