Agentic Commerce World: leaderboard
Metric: Overall (%). Source: arxiv.org. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 85.6 |
| 2 | Gemini 3.6 Flash | 85 |
| 3 | Gemini 3.5 Flash | 83.7 |
| 4 | Kimi K3 | 83 |
| 5 | GPT-5.6 Terra | 80.2 |
| 6 | Claude Sonnet 5 | 78.4 |
| 7 | Qwen 3.5 Plus | 73 |
| 8 | DeepSeek V4 Pro | 70.3 |
| 9 | Mistral Medium 3.5 | 67.8 |
| 10 | GPT-5.6 Luna | 65.9 |
Interactive version: theaggregate.ai/benchmark?slug=agentic-commerce-world · How It Works · Data refreshed daily, snapshot 2026-09-05.