The Decoder· Manuel Uth·· 8 h ago
No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark
No AI agent scores above 12 percent on SemiAnalysis' new real-world work benchmark
AI summary
SemiAnalysis is putting AI agents through simulated knowledge work in its new GDPx benchmark, covering everything from chip design to quant trading. No model breaks 12 percent. Claude Opus 5.5 leads narrowly over Gemini 4 Carbon. Critics point to the small number of tasks per domain and uneven testing conditions.
Selection record
Threshold 76Media and individualsFirst 62Second 58
Not admittedSum of both 120 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：AI Agent基准测试与评测结果
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com