B2V-Bench (With Value Definitions): 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 a definition of each value). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1GPT-540
2GLM-533.5
3Kimi K2.632.5
4DeepSeek V3.228.9
5Claude Haiku 4.528.6
6Qwen 3 235B A22B27.1
7GPT-4o Mini25.3

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