PAUSE - Shopping: leaderboard

Metric: Task score (%; 60 constrained shopping tasks, state-based check of the purchased product, quantity and size, voucher use and budget, aggregated per task; multi-turn tasks in a simulated personal service environment with 50 assistant tools, user-controlled permissions and system configurations and a Gemini-3-Flash user simulator; higher is better). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Gemini 3 Pro72.1
2GPT-569.1
3Gemini 3 Flash59
4DeepSeek V3.2 (Thinking)55
5GPT-5 Mini47.3
6DeepSeek V3.2 (Non-reasoning)41.7
7Gemini 2.5 Pro37.7
8GPT-4.119.7
9GPT-4.1 Mini18.3

Interactive version: theaggregate.ai/benchmark?slug=pause-shopping · How It Works · Data refreshed daily, snapshot 2026-09-29.