PulseAugur
EN
LIVE 23:01:46

AI agents fail new real-world work benchmark, scoring below 12%

By PulseAugur Editorial · [1 sources] ·

SemiAnalysis has introduced a new benchmark, GDPx, designed to evaluate AI agents on simulated knowledge work tasks across various domains like chip design and quantitative trading. However, current AI agents are performing poorly, with none achieving scores above 12 percent. Claude Opus 5.5 and Gemini 4 Carbon are noted as leading the pack, though the benchmark faces criticism for its limited number of tasks per domain and inconsistent testing conditions. AI

IMPACT Highlights current limitations of AI agents in complex knowledge work, indicating a need for significant advancements in agent capabilities.

RANK_REASON New benchmark released by a research firm evaluating AI agent capabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on The Decoder →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI agents fail new real-world work benchmark, scoring below 12%

How we ranked this

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
New benchmark released by a research firm evaluating AI agent capabilities. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. The Decoder TIER_1 English(EN) · Manuel Uth ·

    No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark

    <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/11/semianalysis.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> SemiAnalysis is putting AI agents through simulated knowledge w…

RELATED ENTITIES

RELATED TOPICS