Skip to content
Yardstick
  1. Models
  2. OpenAI
  3. GPT-6 Luna

GPT-6 Luna

OpenAI · Fast & cheap · Sep 22, 2026New

The small, fast GPT-6 tier for high-volume work.

Announcement (opens in a new tab)
Artificial Analysis Intelligence Index
38.1#19 of 29 · max effort
API price per 1M tokens
$0.10 / $0.50input / output · $0.20 blended
Context window
1.1Mup to 128K output tokens
Output speed
129 t/s1m 51s to first answer at max effort

Benchmark results

Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.

Overall capability

  • Artificial Analysis Intelligence Index38.1#19 of 29

    Max effort

    11.357.6
  • Epoch Capabilities Index156.3#10 of 16
    146.9167.3
  • LiveBench72%#18 of 23

    Max effort

    63.9%83.4%

Coding

  • Terminal-Bench 4.016.4%#12 of 13

    Codex harness, max effort

    14.6%64.8%
  • Arena WebDev1,582#18 of 27

    Max effort

    1,2631,814

Agents & professional work

  • GDPval-AA1,432#16 of 18

    Max effort

    1,2421,866

Reasoning

  • ARC-AGI-259.3%#10 of 11

    Max effort

    42.4%95%
  • ARC-AGI-30.2%#5 of 5

    Medium effort

    0.2%62.7%
  • FrontierMath (Tiers 1–3)79%#6 of 14

    Max effort

    53%93.7%

Knowledge & science

  • GPQA Diamond90.5%#13 of 14

    Max effort

    90.2%95.8%

Human preference

  • Arena Text1,443#19 of 24

    Max effort

    1,4251,525

Reasoning effort trade-offs

The same model at different thinking budgets. More effort buys a higher intelligence score at a higher cost per task and a longer wait. Measured by Artificial Analysis.

EffortScoreCost / taskFirst answerSpeed
No reasoning
18.5
$0.0110.8s119 t/s
Low
21.5
$0.0043.1s121 t/s
Medium
29.9
$0.018—Not measured—Not measured
High
32.9
$0.02921s112 t/s
Xhigh
34.6
$0.04236s115 t/s
Max (headline score)
38.1
$0.0681m 51s129 t/s

Specs & pricing

Developer
OpenAI
Released
Sep 22, 2026
Availability
Generally available
API model ID
gpt-6-luna
Weights
Proprietary (API only)
Reasoning
Adjustable effort
Knowledge cutoff
May 2026
Accepts
Text, Image
Produces
Text
Context window
1,050,000 tokens
Max output
128,000 tokens
Input price
$0.10 / 1M tokens
Output price
$0.50 / 1M tokens
Cached input
$0.01 / 1M tokens

Prompts above 272K input tokens are billed at twice the input price and 1.5 times the output price for the whole request.

Closest alternatives

Models from other labs nearest to GPT-6 Luna on Artificial Analysis Intelligence Index.

  • Mistral Large 4

    Mistral AI

    Intelligence 38.4 · $1.36 / $4.18

    Compare side by side
  • DeepSeek-V4.1-Flash

    DeepSeek

    Intelligence 39.5 · $0.30 / $1.20

    Compare side by side
  • Qwen3.8-Flash-Next

    Alibaba

    Intelligence 39.8 · $0.15 / $0.47

    Compare side by side

Sources

  • Announcement (opens in a new tab)
  • Model documentation (opens in a new tab)
  • System card (opens in a new tab)
  • Pricing (opens in a new tab)
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs