SemiAnalysis drops AI agents below 12% on realistic work tests
1 source
Key points
- No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark GDPx.
- Claude Opus 5.5 leads with 12 percent, followed by Gemini 4 Carbon (10.9%) and GPT-6 Astra (9.6%).
- Critics question the test's realism and safety filters impact on results.
Model pages: Claude Opus 5.5 → · Gemini 4 Carbon → · GPT-6 Astra →
The story so far
7 episodes →- SemiAnalysis drops AI agents below 12% on realistic work teststhis story
Full story from The Decoder · by Manuel UthOpen source ↗
No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark
The Decoder · 5 November 2026
Loading the full article…
This text was published by The Decoder and written by Manuel Uth. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Topics · follow one to build your own front page
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- NVIDIA proposes converting telecom facilities into AI hubs · 1 src
- OpenAI says GPT-6 Astra designed a hardware device from scratch in under a week · 13 src
- Former BI engineer rewrites 25 incident response manuals with Notion AI and Claude in six weeks · 1 src
- OpenAI partners with Australian universities to deploy ChatGPT Edu · 1 src
- Square Peg backs Future Secure AI to build enterprise AI co-workers · 1 src
Comments
via GitHub Discussions