cd /news/artificial-intelligence/gdpx-the-general-agentic-benchmark · home › topics › artificial-intelligence › article
[ARTICLE · art-162336] src=gdpx.semianalysis.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

GDPx: The General Agentic Benchmark

A benchmark called GDPx v1.0 was published to measure frontier model capabilities across 11 domains, built with 14 partners and 206 tasks. The GDPx results are presented on a cost-versus-performance Pareto frontier plotting GDPx score against average cost per task on a log scale, with Muse Wonder Full excluded because it has no public price. The benchmark also lets users compare models by domain.

read1 min views1 publishedNov 2, 2026
GDPx: The General Agentic Benchmark
Image: source

v1.0

Measuring frontier model capabilities across the most valuable domains

  • 11
  • domains
  • 14
  • partners
  • 206
  • tasks

Cost vs. Performance Pareto Frontier #

↑ GDPx scoreAvg cost per task (log) → Not shown: Muse Wonder Full, with no public price.

by

Compare models by domain #

ModelGDPx

by

Thanks to

source & further reading
gdpx.semianalysis.com — original article
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @gdpx 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gdpx-the-general-age…] indexed:0 read:1min 2026-11-02 · —