# SemiAnalysis drops AI agents below 12% on realistic work tests

Digest AI · Enterprise & Industry · published 2026-11-05T16:46:24Z

Canonical: https://digestai.news/story/semianalysis-drops-ai-agents-below-12-on-realistic-work-tests

## 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.

## Why it matters

The benchmark highlights significant gaps in AI capabilities for real-world tasks, challenging industry expectations.

## Sources

1. [No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark](https://the-decoder.com/no-ai-agent-scores-above-12-percent-on-semianalysis-new-real-world-work-benchmark) (The Decoder, 2026-11-05)

Part of the developing story: [AI Model Showdown Claude Opus Dominates Benchmarks](https://digestai.news/thread/replit-ends-partnership-with-anthropic-cites-cost-and-performance) (7 stories)

## Cite

Digest AI, "SemiAnalysis drops AI agents below 12% on realistic work tests", 5 November 2026, https://digestai.news/story/semianalysis-drops-ai-agents-below-12-on-realistic-work-tests

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/semianalysis-drops-ai-agents-below-12-on-realistic-work-tests.json