Skip to content

OpenAI Proprietary Released Sep 22, 2026 Updated

GPT-6 Luna

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #86 / 419

    390 / 1,000

    ToolsGuide Score· votes only

  • Vision #59 / 167

    414 / 1,000

    ToolsGuide Score· votes only

  • Coding #39 / 151

    404 / 1,000

    ToolsGuide Score· votes 427, tests 370

  • Agents #20 / 57

    481 / 1,000

    ToolsGuide Score· votes only

  • Price per 1M tokens

    In $0.10· Out $0.50

    $0.10

    Input · median text model $0.44

Summary

GPT-6 Luna is OpenAI's model, released Sep 22, 2026. It's ranked in 4 categories and does best at text: #86 of 419, with a ToolsGuide Score of 390 against a median of 252.

It also ranks #39 of 151 for coding (404), #20 of 57 for agents (481), #59 of 167 for vision (414).

Its text and vision and agents score uses votes only, because it has published fewer than two of the tests used for those categories.

It costs $0.10 per million input tokens and $0.50 per million output tokens, below the median text model ($0.44).

It has published results on 5 tests.

Specifications

Creator
OpenAI
Licence
Proprietary
Released
Sep 22, 2026
Context window
1.1M tokens
Input price
$0.10 / 1M
Output price
$0.50 / 1M
Tests reported
5
Settings ranked
GPT-6 Luna (Max), GPT-6 Luna (Medium), GPT-6 Luna (Low)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Coding score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where GPT-6 Luna sits among the top 20 in each category.

Text

#86 of 419 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Vision

#59 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full vision leaderboard →

Coding

#39 of 151 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

Agents

#20 of 57 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full agents leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

GPT-6 Luna (Max) · hover a bar for its rank

Vision

GPT-6 Luna (Max) · hover a bar for its rank

Coding

GPT-6 Luna (Max) · hover a bar for its rank

Test results

Every test GPT-6 Luna has a published result on, out of 100%, with its rank among the models that took it.

  • DeepSWE 1.1

    #29 / 52

    DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

    66.6%

    Self-reported · In the coding score

  • Agents' Last Exam

    #8 / 26

    Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.

    50.9%

    Self-reported · In the agents score

  • FrontierCode 1.1

    #15 / 24

    FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

    42.4%

    Self-reported · In the coding score

  • OSWorld 2.0

    #12 / 17

    OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks. Each task is an end-to-end workflow that takes human users a median of about 1.6 hours, scored with a binary-completion metric, and targets challenges such as dynamic environments, cross-source reasoning, and implicit-state inference.

    52.7%

    Self-reported

  • AutomationBench v1.0.6

    #6 / 6

    AutomationBench v1.0.6 evaluates agent performance on multi-step workflow automation tasks.

    20.7%

    Self-reported