SemiAnalysis launches GDPx benchmark: best frontier model scores just 12%
scaling01 · x · 2026-11-04
SemiAnalysis (Dylan Patel's team) released GDPx, a benchmark measuring frontier agentic capabilities across the domains where AI revenue will concentrate: chip design, cybersecurity, biology, finance, legal, quant trading, RSI, hardware design, materials science, alignment, and software engineering — deliberately skipping government, real estate, and insurance.
Their thesis: the first trillion dollars of AI revenue will concentrate in high-ROI sectors rather than diffuse across the economy, so GDP-share or occupation-taxonomy benchmarks are the wrong target.
Results: it's a true frontier-level benchmark — the best model scores only 12%. Opus 5.5 and GPT-6 Astra have sandbagged scores due to safety classifiers in cyber/bio/alignment; excluding those domains, OpenAI and Anthropic dominate the top while SpaceXAI, Meta, and open-weight models trail meaningfully behind.
Related event: SemiAnalysis Launches GDPx Benchmark; Best Models Score Just 12%(20 posts)→
More from Models
- Frontier models' teaching ability is 'off the charts', says dev: your 'I know kung fu' moment — shauseth · 2026-11-04
- kalomaze: crude diffusion autoencoders may lose low-frequency info at the latent stage — kalomaze · 2026-11-04
- Dev complains frontier models can't do light-touch English editing — A_K_Nain · 2026-11-04
- Pika H3 Flex debuts #1 on DesignArena; community ships 2-step Turbo LoRA within 24 hours — _akhaliq · 2026-11-04
- 1,300+ graded word-association clues: Google models beat OpenAI's, both beat Anthropic's — Hardicecream17 · 2026-11-04
- Ex-OpenAI researcher Richard Ngo: alignment is the bottleneck to eliciting model capabilities — arthurcolle · 2026-11-04