RealWorldShop - Session Quality: leaderboard
Metric: Session-level process quality (0-2): mean of the GPT-5.5 judge's clarification, state tracking, constraint handling, pacing and personalization scores over each full shopping session; higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 1.2 |
| 2 | Kimi K2.6 | 0.99 |
| 3 | DeepSeek V3.2 | 0.8 |
| 4 | Gemini 2.5 Flash | 0.7 |
| 5 | Qwen 3.5 27B | 0.7 |
| 6 | Qwen 3.5 35B A3B | 0.64 |
| 7 | GPT-4o | 0.56 |
Interactive version: theaggregate.ai/benchmark?slug=realworldshop-session-quality · How It Works · Data refreshed daily, snapshot 2026-10-02.