SRBench - Beauty (NDCG@5): leaderboard
SRBench (2026) evaluates LLMs as sequential recommenders that predict the next item a user interacts with from the full interaction history, using a structured prompt and a numeric answer extractor. This board is NDCG@5 from 0 to 1 on Amazon Beauty product reviews; higher is better.
Metric: NDCG@5 (0-1) of the held-out next item among five recommendations on Beauty, LLM sequential recommendation with the full-length interaction history; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4 | 0.2314 | #410 |
| 2 | GPT-4.1 | 0.2301 | #505 |
| 3 | SRBench DeepSeek-v3 (checkpoint unspecified) | 0.1873 | |
| 4 | Grok 3 | 0.1454 | #611 |
| 5 | Llama-3.2 (SRBench checkpoint unspecified) | 0.1072 | |
| 6 | GLM-3-Turbo | 0.0894 | |
| 7 | Llama-2 (SRBench checkpoint unspecified) | 0.0381 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=srbench-beauty-ndcg-5 · How It Works · Data refreshed daily, snapshot 2026-11-21.