GDPx benchmark launches: 206 tasks across 11 high-value domains, Claude Opus 5.5 tops at 12.0
kenbwork · x · 2026-11-02
SemiAnalysis launched GDPx v1.0, a benchmark built with 14 specialized data partners measuring frontier models across 11 high-value domains and 206 tasks: cybersecurity, chip design, software engineering, materials science, legal, finance, quant trading, biology and more.
- Leaderboard: Claude Opus 5.5 leads at 12.0, followed by Gemini 4 Carbon (10.9), GPT-6 Astra (9.6), Muse Wonder Full (9.0)
- The site offers a cost-vs-performance Pareto frontier, comparing 20 models by average cost per task per domain
- Inference for open-source models and sandbox infrastructure were sponsor-provided
GDPx scores models on economically valuable domains rather than general exams, useful for gauging real professional-task performance and price-performance.
Related event: SemiAnalysis launches GDPx benchmark; best models score just 12%(4 posts)→
More from Models
- Is Claude Opus 5.5 alright? User flags sloppy behavior over unknown tools and API names — JeremyNguyenPhD · 2026-11-02
- SemiAnalysis releases GDPx agentic benchmark; best model scores just 12%, Pichai nods — sundarpichai · 2026-11-02
- Insider claims astra outsmarts Opus and Fable but was benchmark-optimized at the cost of alignment — haider1 · 2026-11-02
- JetBrains ships Mellum2.1 Thinking MTP head: 1.4–1.8x faster decoding with ~90% draft acceptance — pmttyji · 2026-11-02
- Grok Bot pricing debate: users say free tier makes no sense, back gifting instead — RachelVT42 · 2026-11-02
- Grok users hit weekly limits early as OpenAI doubles Pro caps — how do teams plan? — Entire_Struggle_2236 · 2026-11-02