MerchantBench (Hermes Agent): leaderboard
Metric: Final net assets (thousand RMB; 365-day order-level simulation of a drop-shipping store grounded in 98,843 real product records, 26 tools for sourcing, listing, pricing and cash flow; the store starts with RMB 2,000 cash and a RMB 1,000 deposit; mean of three runs; the Nous Research Hermes Agent default configuration with its code, planning, memory and skill tools). Source: arxiv.org. Saturation forecast: Around October 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 59.46 |
| 2 | GPT-5.6 Sol | 52.93 |
| 3 | GLM-5.2 | 42.32 |
| 4 | Claude Opus 4.8 | 35.56 |
| 5 | Qwen 3.7 Plus | 29.42 |
| 6 | DeepSeek V4 Flash | 24.69 |
| 7 | Kimi K2.6 | 23.96 |
| 8 | DeepSeek V4 Pro | 16.71 |
Interactive version: theaggregate.ai/benchmark?slug=merchantbench-hermes-agent · How It Works · Data refreshed daily, snapshot 2026-09-29.