PaperSwipe

The AI Consumer Index (ACE)

Published 2 days agoVersion 1arXiv:2512.04921

Authors

Julien Benchek, Rohit Shetty, Benjamin Hunsberger, Ajay Arun, Zach Richards, Brendan Foody, Osvald Nitski, Bertie Vidgen

Categories

cs.AIcs.CLcs.HC

Abstract

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform high-value consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) (55.2%) and GPT 5.1 (Thinking = High) (55.1%). Models differ across domains, and in Shopping the top model scores under 50%. For some requests (such as giving the correct price or providing working links), models are highly prone to hallucination. Overall, ACE shows a substantial gap between the performance of even the best models and consumers' AI needs.

The AI Consumer Index (ACE)

2 days ago
v1
8 authors

Categories

cs.AIcs.CLcs.HC

Abstract

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform high-value consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) (55.2%) and GPT 5.1 (Thinking = High) (55.1%). Models differ across domains, and in Shopping the top model scores under 50%. For some requests (such as giving the correct price or providing working links), models are highly prone to hallucination. Overall, ACE shows a substantial gap between the performance of even the best models and consumers' AI needs.

Authors

Julien Benchek, Rohit Shetty, Benjamin Hunsberger et al. (+5 more)

arXiv ID: 2512.04921
Published Dec 4, 2025

Click to preview the PDF directly in your browser