---
type: "Evidence Item"
title: "Measuring the performance of our models on real-world tasks"
description: "OpenAI introduces GDPval, a new evaluation that measures model performance on real-world economically valuable tasks across 44 occupations."
resource: "https://openai.com/index/gdpval"
tags: ["appendix-iii", "benchmark", "openai"]
timestamp: "2025-09-25"
category: "benchmark"
publisher: "OpenAI"
cope_score: 76
confidence: 0.9
---

# Measuring the performance of our models on real-world tasks

# Claim

OpenAI introduces GDPval, a new evaluation that measures model performance on real-world economically valuable tasks across 44 occupations.

# Relevance

Appendix III, section one: model and benchmark capability evidence

# Oracle Verdict

This belongs in the register because benchmark and model-release claims set the ceiling for the next wave of deployment stories. The labour-market effect is indirect today, but it becomes direct when these gains are packaged into agents, APIs, and enterprise tools.

# Metadata

* Publisher: OpenAI
* Category: benchmark
* Sector: General AI capability
* Capability: Education and workforce adoption
* Cope score: 76
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [Measuring the performance of our models on real-world tasks](https://openai.com/index/gdpval)