MemoryCD (Home & Kitchen) - Item Ranking: leaderboard
Metric: NDCG@3 (0-1, times 100) of the model's ranking of candidate items by the user's expected interest, on MemoryCD's Home & Kitchen domain (110 users with long histories, their 3 most recent interactions each), the whole history concatenated into the prompt; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 61 | #91 |
| 2 | GPT-5 Mini | 55.7 | #176 |
| 3 | Gemini 2.5 Pro | 44.4 | #145 |
| 4 | GPT-5 Nano | 41.8 | #415 |
| 5 | Claude Sonnet 4 | 40 | #194 |
| 6 | Gemini 2.5 Flash | 38.1 | #237 |
| 7 | Claude Opus 4 | 37.8 | #155 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=memorycd-home-kitchen-item-ranking · How It Works · Data refreshed daily, snapshot 2026-10-11.