OpenAI

Their benchmarks in the atlas

BrowseCompby OpenAITask level · Accuracy
92.2%GPT-5.6 Sol Ultra · Jul 2026
Saturated
GDPvalby OpenAIProject level · Wins plus ties against experts
84.9%GPT-5.5 · Apr 2026
Strong
MLE-benchby OpenAIProject level · Any medal (%)
64.4%Famou-Agent 2.0 (Gemini-3-Pro-Preview) · 23 Feb 2026
Strong
PaperBenchby OpenAIProject level · Average replication score
26%IterativeAgent o1-high (36h limit) · 2 Apr 2025
Emerging
SWE-bench Verifiedby Princeton University and OpenAITask level · Resolved
79.2%Sonar Foundation Agent + Claude 4.5 Opus · 5 Dec 2025
Retired
SWE-Lancerby OpenAITask level · IC SWE Diamond pass@1
80%gpt-5.1-codex-max · 18 Nov 2025
Strong

Work their benchmarks cover

Office and administrative support Management and business operations Finance and accounting Legal Software engineering Sales and marketing Healthcare Design, media, and writing Architecture and engineering Customer support Education and social services ML and research engineering Data and analytics Science and research

Embed this card

The image names the institutions behind the numbers and links back to this page.

HTML:

<a href="https://canagentswork.com/institutions/openai/"><img src="https://canagentswork.com/og/institutions-openai.png" width="600" height="315" alt="OpenAI's agent benchmarks, mapped onto the world of work:" loading="lazy"></a>

Markdown:

[![OpenAI's agent benchmarks, mapped onto the world of work:](https://canagentswork.com/og/institutions-openai.png)](https://canagentswork.com/institutions/openai/)

For OpenAI: link to this page

You can link to this page from your site. Copy this HTML:

<a href="https://canagentswork.com/institutions/openai/">Featured in the Work Atlas — Can Agents Work?</a>

If a summary or number on this page is wrong, tell us. We correct errors within 48 hours of a report. To grant permission to show your logo, contact us; until then we show only your name.