OmniBehavior - E-commerce Binary Behaviors: leaderboard

OmniBehavior (2026) tests LLMs as simulators of real users: given the profile and long, real behaviour history of a user across the Kuaishou video, live-streaming, ads and e-commerce scenarios, the model predicts what the user does next. F1 on binary engagement decisions such as adding to cart in the e-commerce scenario, in percent; higher is better.

Metric: F1 (%) on binary engagement decisions (such as add-to-cart) in the e-commerce scenario, for predicting the real behaviour of 200 Kuaishou users (three months of interleaved video, live-stream, ads and e-commerce traces, 8,143 actions per user on average) from the user profile, history and current scenario, 6,000 balanced tasks, 32k context window, temperature 0.1; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.536.13#261
2OmniBehavior DeepSeek-V3 (checkpoint unspecified)33.31
3GLM-4.732.9#380
4Claude Opus 4.529.98#160
5Kimi K2 090529.94#570
6GPT-5.229.32#185
7GPT-4o28.66#751
8Claude Haiku 4.526.37#583
9Gemini 3 Flash19.65#175
10Qwen 3 235B A22B 2507 Instruct19.22#616
11Claude Sonnet 416.5#410

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

Interactive version: theaggregate.ai/benchmark?slug=omnibehavior-e-commerce-binary-behaviors · How It Works · Data refreshed daily, snapshot 2026-11-21.