HORIZON - LLM Long-Horizon User Modeling: leaderboard

HORIZON (2026) is a cross-domain, long-horizon user modeling benchmark built from Amazon Reviews; its LLM tasks run zero-shot on a held-out set of users whose histories end at a 2020 cut-off, and the text from the LLM is turned into catalog items by a fixed retrieval encoder. Here the LLM describes the next ten items the user is likely to engage with; recall at 100 of those future items, in percent; higher is better.

Metric: Recall@100 (%) of the user's next ten items when the LLM describes the ten items it expects the user to engage with, items retrieved from the Amazon Reviews catalog with the BLAIR item encoder and a FAISS index, zero-shot, on HORIZON's held-out set of one million out-of-distribution users after the 2020 cut-off; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 8B15.75#1890
2Llama 3.1 8B Instruct13.25#4655
3Gemma 2 9B (IT)10.39#2383

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=horizon-llm-long-horizon-user-modeling · How It Works · Data refreshed daily, snapshot 2026-11-22.