UnifyBench

RankingOSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline

OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline

Data updated 24 Sept 2026

Bucket
Agentic
Unit
percent
Direction
Higher is better
Version
2.0 / v2026.08.08 offline
Display harness
GPT-6 Astra: A new generation of intelligence
Board
https://openai.com/index/gpt-6-astra/

Compare published benchmark results with category weights →

Models

Published configurations retain their source and harness labels. Missing results remain unknown.

1–13 of 13 entries

ModelScoreHarnessEvidenceSource-recorded date
GPT-6 AstraOpenAI72.6%
Reported settings & source

Maximum reported across reasoning efforts; OpenAI research environment or API; offline set; partial credit; v2026.08.08; official task/grading settings

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / OSWorld 2.0 (v2026.08.08, offline set, partial score) / GPT‑6 Astra · reviewed 2026-09-06

GPT-6 Astra: A new generation of intelligencelab self-report2026-09-06
Claude Opus 5Anthropic70.2%
Reported settings & source

Maximum reported across reasoning efforts; OpenAI research environment or API; offline set; partial credit; v2026.08.08; official task/grading settings

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / OSWorld 2.0 (v2026.08.08, offline set, partial score) / Claude Opus 5 · reviewed 2026-09-06

GPT-6 Astra: A new generation of intelligencelab self-report2026-09-06
GPT-5.6 SolOpenAI65.7%
Reported settings & source

Maximum reported across reasoning efforts; OpenAI research environment or API; offline set; partial credit; v2026.08.08; official task/grading settings

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-6 Astra: A new generation of intelligence · Computer Use table / OSWorld 2.0 (v2026.08.08, offline set, partial score) / GPT‑5.6 Sol · reviewed 2026-09-06

GPT-6 Astra: A new generation of intelligencelab self-report2026-09-06
GPT-6 LunaOpenAI8.26%
Reported settings & source

Reported reasoning effort low. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.0826, stored as 8.26 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / low · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 LunaOpenAI31.54%
Reported settings & source

Reported reasoning effort medium. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.3154, stored as 31.54 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / medium · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 LunaOpenAI41.43%
Reported settings & source

Reported reasoning effort high. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.4143, stored as 41.43 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / high · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 LunaOpenAI46.7%
Reported settings & source

Reported reasoning effort xhigh. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.467, stored as 46.7 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / xhigh · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 LunaOpenAI52.68%
Reported settings & source

Reported reasoning effort max. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.5268, stored as 52.68 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / max · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 SolOpenAI43.9%
Reported settings & source

Reported reasoning effort low. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.439, stored as 43.9 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Sol / low · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 SolOpenAI54%
Reported settings & source

Reported reasoning effort medium. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.54, stored as 54 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Sol / medium · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 SolOpenAI58.29%
Reported settings & source

Reported reasoning effort high. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.5829, stored as 58.29 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Sol / high · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 SolOpenAI60.54%
Reported settings & source

Reported reasoning effort xhigh. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.6054, stored as 60.54 percent. Not an independent board. Article prose rounds this xhigh point to 60.5%.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Sol / xhigh · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22
GPT-6 SolOpenAI64.43%
Reported settings & source

Reported reasoning effort max. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page.

Provider-published lab self-report. Vega-Lite chart data value 0.6443, stored as 64.43 percent. Not an independent board.

Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.

Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Sol / max · reviewed 2026-09-22

Introducing GPT-6 Sol and Lunalab self-report2026-09-22