EComAgentBench - Query Rubrics: leaderboard

Metric: Rubric satisfaction (%) on the requirements visible in the shopping query, on 662 long-horizon shopping tasks over a catalog of real Amazon products and reviews, where requirements are split across the visible query, a tool-gated user profile and scripted clarification; up to 100 tool calls; graded with typed rubrics by a gemini-3.1-pro-preview judge; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.

Top models

#ModelScore
1GPT-5.4 (Medium)88.1
2GPT-585.7
3MiniMax-M2.783.5
4GPT-5 Mini82.1
5Claude Opus 4.680.6
6Kimi K2.679.9
7Qwen 3 30B A3B68.8

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