text model comparison
GPT-6 Luna vs Muse Ember
GPT-6 Luna and Muse Ember are both current text models, from OpenAI and Meta. Both cost $0.10 per 1M input tokens. On Arena WebDev, GPT-6 Luna scores 1578 Elo and Muse Ember 1608 Elo (Arena, measured November 9, 2026). Both accept about 1.05M tokens of context (1,050,000 and 1,048,576).
- Higher Arena WebDev
- Muse Ember1608 Elo against 1578 Elo
- Longer context window
- GPT-6 Luna1.05M tokens against 1.05M tokens
- Newer release
- Muse EmberNov 2026 against Sep 2026
Data verified November 10, 2026 · Dataset 2026-11-10
Side by side
GPT-6 Luna and Muse Ember, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | GPT-6 Luna | Muse Ember |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.10 | $0.10 |
| Price per 1M output tokens | $0.50 | $0.50 |
| Independent benchmarks | ||
| Arena WebDev | 1578 Elo (#31 of 48) | 1608 Elo (#26 of 48) (better) |
| Arena Text | 1441 Elo (#39 of 53) | Not measured |
| GPQA Diamond | 90.5% (#28 of 43) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 78.9% (#18 of 43) | Not measured |
| SimpleQA Verified | 41.4% (#30 of 40) | Not measured |
| Specs | ||
| Provider | OpenAI | Meta |
| Release date | September 22, 2026 | November 9, 2026 |
| Access | API only | API only |
| Context window | 1,050,000 tokens | 1,048,576 tokens |
| Max output | 128,000 tokens | 524,288 tokens |
| Input | text, image | text, image, audio, video |
| Output | text | text |
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both GPT-6 Luna and Muse Ember. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.
Meta, Muse Ember launch charts, November 9, 2026Meta · 2026-11-10
| Benchmark | GPT-6 Luna | Muse Ember |
|---|---|---|
| Agents' Last ExamLinux subset | 57.1% | 61.6% (better) |
| Terminal-Bench 4.0best published harness | 16.4% | 40.9% (better) |
| OSWorld 2.1partial credit | 50.5% | 69.5% (better) |
| OSWorld 2.1binary | 17.0% | 33.8% (better) |
| PerceptionBenchwith tools | 62.8% | 80.6% (better) |
Meta's charts from the Muse Ember announcement, every model at max reasoning effort and run by Meta. Terminal-Bench 4.0 uses each model's best published harness: mini-swe-agent for Muse Ember, Claude Code for Claude Haiku 5.5 and Codex for GPT-6 Luna. Left out here: the rows Artificial Analysis ran (AutomationBench-AA, Coding Agent Index-AA, FrontierCode 2.0-AA, GDP.pdf-AA and its Intelligence Index) and Meta's internal Personal Superintelligence Index.
Charts
Against every current text model
Where GPT-6 Luna and Muse Ember land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
On Arena WebDev, GPT-6 Luna ranks #31 and Muse Ember #26 of 48 current models. Each bar is the share of current models it beats: on score, price and context.
Independent benchmarks
Arena Text
GPT-6 Luna:#39of 53
1,441 Elo · ahead of 27%
Muse Ember: Not scored
Arena WebDev
GPT-6 Luna:#31of 48
1,578 Elo · ahead of 36%
Muse Ember:#26of 48
1,608 Elo · ahead of 47%
GPQA Diamond
GPT-6 Luna:#28of 43
90.5% · ahead of 33%
Muse Ember: Not scored
FrontierMath Tiers 1-3 (v2)
GPT-6 Luna:#18of 43
78.9% · ahead of 60%
Muse Ember: Not scored
SimpleQA Verified
GPT-6 Luna:#30of 40
41.4% · ahead of 26%
Muse Ember: Not scored
Price and context
Price per 1M input tokens
GPT-6 Luna:#1of 61
$0.10 · cheaper than 95%
Muse Ember:#1of 61
$0.10 · cheaper than 95%
Price per 1M output tokens
GPT-6 Luna:#3of 61
$0.50 · cheaper than 92%
Muse Ember:#3of 61
$0.50 · cheaper than 92%
Context window
GPT-6 Luna:#1of 70
1.05M tokens · longer than 86%
Muse Ember:#12of 70
1.05M tokens · longer than 67%
Quality against price
GPT-6 Luna scores 1,441 at $0.2 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Carbon | $4 | 1,526 | |
| Gemini 4 Argon | $4 | 1,522 | |
| Muse Wonder | Meta | $8 | 1,511 |
| Claude Opus 5.5 | Anthropic | $8 | 1,506 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,503 |
| Gemini 3.8 Flash | $1.50 | 1,497 | |
| Muse Spark 1.3 | Meta | $2 | 1,496 |
| Claude Opus 5 | Anthropic | $10 | 1,490 |
| Kimi K3 | Moonshot Kimi | $6 | 1,487 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,484 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GLM-5.3 | Z.ai | $2.15 | 1,483 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,482 |
| GPT-5.5 | OpenAI | $11 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,475 |
| GPT-6 Astra | OpenAI | $20 | 1,474 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,474 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,468 |
| Grok 4.5 | xAI | $3 | 1,466 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,464 |
| Claude Sonnet 5 | Anthropic | $4 | 1,461 |
| GPT-6 Sol | OpenAI | $4 | 1,457 |
| Grok 4.6 | xAI | $3 | 1,456 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,455 | |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| Grok 4.7 | xAI | $3 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,423 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,422 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Inkling 2 Small | Thinking Machines Lab | $0.47 | 1,412 |
| Solar Pro 4 | Upstage | $0.52 | 1,387 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
At each provider's listed rates.
10M input and 2M output tokens
The same price
- GPT-6 Luna
- $2
- Muse Ember
- $2
The same, with 9M of the input tokens cached
GPT-6 Luna costs 1.0× as much
- GPT-6 Luna
- $1.19
- Muse Ember
- $1.14
| Workload or rate | GPT-6 Luna | Muse Ember |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $2 | $2 |
| The same, with 9M of the input tokens cached | $1.19 | $1.14 (better) |
| Other listed rates | ||
| 1M input tokens, cached | $0.01 | $0.004 (better) |
| 1M input tokens, cached, prompts over 200K tokens | Not listed | $0.012 |
| 1M input tokens, prompts over 272K tokens | $0.20 | Not listed |
| 1M output tokens, prompts over 272K tokens | $0.75 | Not listed |
| 1M input tokens, prompts over 200K tokens | Not listed | $0.30 |
| 1M output tokens, prompts over 200K tokens | Not listed | $1.50 |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
GPT-6 Luna
Where it leads
No measured lead over Muse Ember in this data.
Best for
- High-volume summarisation, extraction and routing
- Long-context budget work, where the 272k threshold is more forgiving than Haiku 5.5's 100k
Watch out for
- Prompts over 272,000 tokens are rebilled at $0.20 input and $0.75 output for the whole request
- A twentieth of GPT-6 Sol's price reflects a capability gap, not a discount on the same model
Muse Ember
Where it leads
- Higher Arena WebDev score, 1608 Elo vs 1578 Elo
- Longer responses, up to 524,288 vs 128,000 output tokens
- Accepts audio and video input
- Cheaper cached input, $0.004 vs $0.01 per 1M tokens
Best for
- Sub-agent work under a larger planner such as Muse Spark or Muse Wonder
- High-volume extraction, classification and routing over images, documents and records
Watch out for
- A request over 200K input tokens is billed in full at three times the rate: $0.30 input, $1.50 output and $0.012 cached input per 1M tokens
- Claude Haiku 5.5 scores higher on FrontierCode 2.0 as run by Artificial Analysis (34.9% against 27.2%), a row in Meta's own launch post
- Arena Text has not rated it yet, and its WebDev rating rests on 1,345 votes so far
From benchmark to production
Building on GPT-6 Luna or Muse Ember?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
GPT-6 Luna vs Muse Ember FAQ
Which is cheaper, GPT-6 Luna or Muse Ember?
Both cost $0.10 per 1M input tokens. For 10M input and 2M output tokens, GPT-6 Luna costs $2 and Muse Ember $2 at standard rates.
Which is cheaper with prompt caching, GPT-6 Luna or Muse Ember?
GPT-6 Luna charges $0.01 per 1M cached input tokens, 90% below its standard input rate, and Muse Ember $0.004, 96% below. With 9M of 10M input tokens cached and 2M output tokens, GPT-6 Luna costs $1.19 and Muse Ember $1.14.
Which scores higher on independent benchmarks, GPT-6 Luna or Muse Ember?
Muse Ember leads on Arena WebDev, 1608 Elo to 1578 Elo. Scores are independent evaluations, not either vendor's launch figures.
How do GPT-6 Luna and Muse Ember compare in Meta's own results?
In the Muse Ember launch charts (November 9, 2026), Muse Ember leads on Agents' Last Exam (Linux subset), 61.6% to 57.1%; Muse Ember leads on Terminal-Bench 4.0 (best published harness), 40.9% to 16.4%; Muse Ember leads on OSWorld 2.1 (partial credit), 69.5% to 50.5%. These are Meta's figures, not independent measurements.
Which has the larger context window, GPT-6 Luna or Muse Ember?
Both accept about 1.05M tokens of context (1,050,000 and 1,048,576). Muse Ember returns up to 524,288 tokens per response, GPT-6 Luna 128,000.
How do GPT-6 Luna and Muse Ember differ in features?
GPT-6 Luna takes text and image input; Muse Ember takes text, image, audio and video.
Further reading
More on GPT-6 Luna and Muse Ember
Articles on GPT-6 Luna and Muse Ember
- OpenAI Models on Google Cloud: What Changes for AI TeamsOctober 22, 2026
- Claude Sonnet 5.5 vs GPT-6 Luna: Cost, Speed and AccuracySeptember 29, 2026
- GPT-6 Sol vs Claude Opus 5.5, Plus Luna: Best Value per TaskSeptember 24, 2026
- GPT-6 Sol and Luna: Half the Price, and Where Each One FitsSeptember 23, 2026
Related comparisons
- Claude Haiku 5.5 vs GPT-6 Luna
- Claude Haiku 5.5 vs Muse Ember
- GPT-6.1 Sol vs GPT-6 Luna
- MiMo-V2.6-Flash vs Muse Ember
- Claude Sonnet 5.5 vs GPT-6 Luna
- Muse Ember vs Muse Spark 1.3
- Claude Opus 5.5 vs GPT-6 Luna
- GPT-4.1 nano vs Muse Ember
- DeepSeek-V4.1-Flash vs GPT-6 Luna
- GPT-5.4 vs GPT-6 Luna
- GPT-6 Astra vs GPT-6 Luna
- GPT-6 Luna vs GPT-6 Sol
Production evaluation
Choosing between GPT-6 Luna and Muse Ember?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty