EComAgentBench - Persona Rubrics: leaderboard
EComAgentBench (2026) benchmarks shopping agents on 662 long-horizon tasks over real Amazon products and reviews, with requirements split across the query, a tool-gated user profile and scripted clarification, and typed rubrics checked by an LLM judge. This board is rubric satisfaction (%) on requirements hidden in the user profile; higher is better.
Metric: Rubric satisfaction (%) on the requirements hidden in the tool-gated user profile, 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 February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 72.8 | #102 |
| 2 | GPT-5.4 (Medium) | 69.8 | #123 (GPT-5.4) |
| 3 | Kimi K2.6 | 63.2 | #178 |
| 4 | GPT-5 | 58.6 | #167 |
| 5 | MiniMax-M2.7 | 57.3 | #518 |
| 6 | GPT-5 Mini | 56.6 | #348 |
| 7 | Qwen 3 30B A3B | 43.1 | #1122 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ecomagentbench-persona-rubrics · How It Works · Data refreshed daily, snapshot 2026-11-13.