research · traced · first seen Nov 2, 10:32 UTC
SemiAnalysis launches GDPx agentic capability benchmark
SemiAnalysis announced GDPx, a benchmark for comparing AI models across 11 domains.
What we checked
Every claim below was walked down the source ladder. The rung is how close the source is to the thing itself; the tense is the source's own.
-
announced L2 · reported
GDPx includes chip design, cybersecurity, and RSI.
per Techmeme (L2) -
announced L2 · reported
Opus 5.5 tops GDPx with a 12% score.
per Techmeme (L2)
Not confirmed
The scoring method and whether GDPx is publicly available are not established.
Who should wait
Teams choosing a model based on the 12% score should wait for scoring details.