Sign Up

Decision support

GPT-6 Luna vs Particle-1

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

ModelsHardware
GPT-6 Luna

OpenAI

Sources:models.devOpenRouter

Particle-1

Particle AI

Sources:OpenRouter

Benchmark results

  • Arena Text

    Arena rating · Higher is better

    • GPT-6 Luna
      1441
      Arena #98CI 1437 to 1445
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max144195% CI 1437 to 1445 · 107,021 votes
    Particle-1

    Not reported

    Source:Arena Text leaderboard, 2026-11-09

  • Arena WebDev

    Arena rating · Higher is better

    • GPT-6 Luna
      1577
      Arena #45CI 1572 to 1583
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max157795% CI 1572 to 1583 · 30,498 votes
    Particle-1

    Not reported

    Source:Arena WebDev leaderboard, 2026-11-10

  • Arena Vision

    Arena rating · Higher is better

    • GPT-6 Luna
      1235
      Arena #68CI 1226 to 1244
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max123595% CI 1226 to 1244 · 6,202 votes
    Particle-1

    Not reported

    Source:Arena Vision leaderboard, 2026-11-09

  • Arena Search

    Arena rating · Higher is better

    • GPT-6 Luna
      1211
      Arena #12CI 1204 to 1218
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max121195% CI 1204 to 1218 · 46,776 votes
    Particle-1

    Not reported

    Source:Arena Search leaderboard, 2026-11-09

  • Agent Arena

    IPS score · Higher is better

    • GPT-6 Luna
      +0.016
      Arena #26CI +0.011 to +0.020
    • Particle-1
      Not reported
    Runs and sources
    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
    Particle-1

    Not reported

    Source:Agent Arena leaderboard, 2026-11-11

  • ARC-AGI-2

    Best published score · Higher is better

    • GPT-6 Luna
      59.3%
      #39 of 85
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • none0.0%
    • low4.6%
    • medium18.1%
    • high31.4%
    • xhigh41.9%
    • max59.3%
    Particle-1

    Not reported

    Source:External evaluation via Epoch AIOriginal-source terms apply

  • FrontierMath-Tier-4-v2-Private

    Best published score · Higher is better

    • GPT-6 Luna
      56.1%
      #20 of 72
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max56.1%
    Particle-1

    Not reported

    Source:Epoch AI evaluation

  • FrontierMath-Tiers-1-3-v2-Private

    Best published score · Higher is better

    • GPT-6 Luna
      78.9%
      #20 of 87
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max78.9%
    Particle-1

    Not reported

    Source:Epoch AI evaluation

  • GPQA diamond

    Best published score · Higher is better

    • GPT-6 Luna
      90.5%
      #42 of 161
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max90.5%
    Particle-1

    Not reported

    Source:Epoch AI evaluation

  • OTIS Mock AIME 2024-2025

    Best published score · Higher is better

    • GPT-6 Luna
      98.9%
      #19 of 158
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max98.9%
    Particle-1

    Not reported

    Source:Epoch AI evaluation

  • SimpleQA Verified

    Best published score · Higher is better

    • GPT-6 Luna
      41.4%
      #49 of 87
    • Particle-1
      Not reported
    Runs and sources
    GPT-6 Luna
    • max41.4%
    Particle-1

    Not reported

    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
September 22, 2026
October 28, 2026
Context window
1.1M
1M
Native context
—
—
Max output tokens
128,000
131,072
Knowledge cutoff
2026-05-18
—
Open weights
Closed
Unknown
Parameter count
—
—

API pricing · USD per 1M tokens

Input
$0.10
$0.05
Output
$0.50
$0.50
Cached input
$0.01
$0.003
Cache write
$0.125
—

Capabilities and modalities

Input modalities
file, image, text
text, image
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity
frequency_penalty, include_reasoning, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
GPT
Other
Instruction format
—
—
License
—
—
Providers
3
1
Provider endpoints
16
1
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.