EComAgentBench - Rubric Satisfaction: leaderboard

Metric: Rubric satisfaction (%): share of the task rubrics (about 10 per task) that the recommended product satisfies, 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)81
2Claude Opus 4.676.6
3GPT-576.1
4MiniMax-M2.773.5
5Kimi K2.673.4
6GPT-5 Mini72.7
7Qwen 3 30B A3B59

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