Sign Up

Decision support

Muse Ember vs GPT-6 Luna

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

ModelsHardware
Muse Ember

Meta

Sources:models.devOpenRouter

GPT-6 Luna

OpenAI

Sources:models.devOpenRouter

Benchmark results

Head to head on 2 benchmarks both models report · 1 tie

  • Muse Ember1lead
  • GPT-6 Luna0leads

  • Arena Text

    Arena rating · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      1441
      Arena #98CI 1437 to 1445
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max144195% CI 1437 to 1445 · 107,021 votes
    Source:Arena Text leaderboard, 2026-11-09

  • Arena WebDev

    Arena rating · Higher is better

    • Muse Ember
      Best1609
      +31 ahead · Arena #36CI 1592 to 1625
    • GPT-6 Luna
      1577
      Arena #45CI 1572 to 1583
    Runs and sources
    Muse Ember
    • max160995% CI 1592 to 1625 · 1,337 votes
    GPT-6 Luna
    • max157795% CI 1572 to 1583 · 30,498 votes
    Source:Arena WebDev leaderboard, 2026-11-10

  • Arena Vision

    Arena rating · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      1235
      Arena #68CI 1226 to 1244
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max123595% CI 1226 to 1244 · 6,202 votes
    Source:Arena Vision leaderboard, 2026-11-09

  • Arena Search

    Arena rating · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      1211
      Arena #12CI 1204 to 1218
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max121195% CI 1204 to 1218 · 46,776 votes
    Source:Arena Search leaderboard, 2026-11-09

  • Agent Arena

    IPS score · Higher is better

    Tie, within 95% CI
    • Muse Ember
      +0.017
      Arena #25CI -0.006 to +0.039
    • GPT-6 Luna
      +0.016
      Arena #26CI +0.011 to +0.020
    Runs and sources
    Muse Ember
    • max+0.01795% CI -0.006 to +0.039 · 186,844 observations
    GPT-6 Luna
    • low-0.06095% CI -0.067 to -0.053 · 3,812,346 observations
    • medium-0.02195% CI -0.025 to -0.016 · 11,530,251 observations
    • max+0.01695% CI +0.011 to +0.020 · 42,848,344 observations
    Source:Agent Arena leaderboard, 2026-11-11

  • ARC-AGI-2

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      59.3%
      #39 of 85
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • none0.0%
    • low4.6%
    • medium18.1%
    • high31.4%
    • xhigh41.9%
    • max59.3%
    Source:External evaluation via Epoch AIOriginal-source terms apply

  • FrontierMath-Tier-4-v2-Private

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      56.1%
      #20 of 72
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max56.1%
    Source:Epoch AI evaluation

  • FrontierMath-Tiers-1-3-v2-Private

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      78.9%
      #20 of 87
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max78.9%
    Source:Epoch AI evaluation

  • GPQA diamond

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      90.5%
      #42 of 161
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max90.5%
    Source:Epoch AI evaluation

  • OTIS Mock AIME 2024-2025

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      98.9%
      #19 of 158
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max98.9%
    Source:Epoch AI evaluation

  • SimpleQA Verified

    Best published score · Higher is better

    • Muse Ember
      Not reported
    • GPT-6 Luna
      41.4%
      #49 of 87
    Runs and sources
    Muse Ember

    Not reported

    GPT-6 Luna
    • max41.4%
    Source:Epoch AI evaluation

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Original-source terms apply to evaluations credited to their original publishers.

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
November 9, 2026
September 22, 2026
Context window
1M
1.1M
Native context
—
—
Max output tokens
943,718
128,000
Knowledge cutoff
—
2026-05-18
Open weights
Closed
Closed
Parameter count
—
—

API pricing · USD per 1M tokens

Input
$0.10
$0.10
Output
$0.50
$0.50
Cached input
$0.004
$0.01
Cache write
$0.125
$0.125

Capabilities and modalities

Input modalities
text, image, video, file, audio
file, image, text
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
include_reasoning, max_tokens, reasoning, reasoning_effort, repetition_penalty, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_k, top_p
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
Other
GPT
Instruction format
—
—
License
—
—
Providers
2
3
Provider endpoints
2
16
Ollama variants
0
0
Metadata source
ai-research
ai-research

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.