RecRM-Bench - Instruction Following: leaderboard

RecRM-Bench (Meituan, 2026) tests models as reward models for an agentic recommender system, on real query-response logs. This board covers the instruction-following compliance score under expert rubrics; the score is the percent of judgements that match the gold label; higher is better.

Metric: Accuracy (%) of the overall instruction-following compliance score the model assigns to a recommender response under the expert rubrics (role, format, process, constraint, content quality, style), 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 2030. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1LongCat-Flash-Chat64.84#818
2GPT-4.155.47#505
3LongCat-Flash-Thinking43.75#749
4Qwen 3 MaxNon-reasoning36.8#415
5DeepSeek V3.2Thinking35.29#419

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=recrm-bench-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-21.