RecRM-Bench - Query-Item Relevance: leaderboard
Metric: Accuracy (%) of the three-level relevance score (irrelevant, weakly relevant, fully relevant) the model assigns to a query-item pair, zero-shot, the model acting as a reward model for an agentic recommender on RecRM-Bench (real Meituan query-response logs), its parsed score compared with the gold label; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | LongCat Flash (Thinking) | 75.97 |
| 2 | Qwen 3 Max (Thinking) | 75.89 |
| 3 | DeepSeek V3.2 (Thinking) | 75.22 |
| 4 | DeepSeek V3.2 (Non-reasoning) | 74.6 |
| 5 | LongCat-Flash-Chat | 73.18 |
Interactive version: theaggregate.ai/benchmark?slug=recrm-bench-query-item-relevance · How It Works · Data refreshed daily, snapshot 2026-10-07.