AI Paper Atlas

Research map / Large language models / AI and society

GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Tejal Patwardhan, Rachel Dias, Elizabeth Proehl, Grace Kim, Michele Wang, Olivia Watkins, Simon Posada Fishman, Marwan Aljubeh, Phoebe Thacker, Laurance Fauconnet, Natalie S. Kim, Samuel Miserendino and 7 more

ICLR 2026 · Large language models › AI and society · approach: Social-science view of AI evaluation · 199 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase reasoning effort (low to high) for o3 and GPT-5 (ablation)o3, GPT-5 · GDPval gold subset (220 tasks)win rate vs human expertImproved
Add tuned prompt for rigorous deliverable checking (ablation)GPT-5 · GDPval gold subset (220 tasks)win rate vs human expert: +5 percentage pointsImproved
Add tuned prompt (ablation)GPT-5 · GDPval gold subset (220 tasks) PowerPointegregious formatting error rate: 86% -> 64%Improved
Add tuned prompt (ablation)GPT-5 · GDPval gold subset (220 tasks) agentsmultimodal self-inspection rate: 15% -> 97%Improved
Add GET requests and best-of-4 sampling with GPT-5 judge (ablation)GPT-5 · GDPval gold subset (220 tasks)win rate vs human expertImproved
Shorten prompts to 42% length (under-contextualized) (ablation)GPT-5 · Under-contextualized GDPvalwin rate vs human expertHurt
Expert try-once-then-fix workflow with GPT-4oGPT-4o · GDPval gold subset (220 tasks)speed improvement: 0.87xHurt
Expert try-once-then-fix workflow with GPT-5GPT-5 · GDPval gold subset (220 tasks)speed improvement: 1.12xImproved
Repeat sampling up to n times before expert fix with GPT-4oGPT-4o · GDPval gold subset (220 tasks)speed improvement: 0.87x -> 0.46xHurt
Repeat sampling n times with GPT-5 vs try onceGPT-5 · GDPval gold subset (220 tasks)cost improvement: 1.18x -> 1.63xImproved
Newer OpenAI model generation (GPT-4o to GPT-5)OpenAI models · GDPval gold subset (220 tasks)win rate vs human expert: 12.5% -> 39.0%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy