B2V-Bench (With Behavioral Value Descriptions): leaderboard

Metric: Macro-F1 (%; multi-label classification of the consumer values, 28 labels of the E-commerce Consumption Value Taxonomy plus none, expressed in each of 544 Taobao purchase-decision episodes labelled from scratch by psychology experts; the model reads the GPT-5.4-written summary of the pre-purchase behaviour log; prompt adds the behaviours that evidence each value). Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.

Top models

#ModelScore
1GPT-536
2GLM-533.9
3DeepSeek V3.231.7
4Claude Haiku 4.531.3
5Kimi K2.630.7
6Qwen 3 235B A22B29
7GPT-4o Mini24.8

Interactive version: theaggregate.ai/benchmark?slug=b2v-bench-with-behavioral-value-descriptions · How It Works · Data refreshed daily, snapshot 2026-09-26.