Knowledge work

GDPval-AA v2

economically valuable knowledge work (v2, re-based Elo)

Rankings

Higher is better

GDPval-AA v2 — frequently asked questions

What is GDPval-AA v2?
economically valuable knowledge work (v2, re-based Elo)
Which AI model scores highest on GDPval-AA v2?
Claude Opus 5 by Anthropic holds the best GDPval-AA v2 result among tracked models, at 1861 (released Jul 24 2026). Higher scores are better on this benchmark.
What are the top 5 models on GDPval-AA v2?
1. Claude Opus 5 (Anthropic) — 1861; 2. GLM-5.3-Flash (Z.ai) — 1773; 3. GLM-5.3 (Z.ai) — 1769; 4. Claude Fable 5 (Anthropic) — 1760; 5. Grok 4.6 (SpaceXAI) — 1753.
How many models have a published GDPval-AA v2 score?
17 tracked models have a published GDPval-AA v2 score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.
What is the best open model on GDPval-AA v2?
GLM-5.3-Flash by Z.ai is the highest-ranked model with downloadable weights on GDPval-AA v2, scoring 1773 at rank 2 overall.