ALPBench - Baijiu (Attribute F1): leaderboard
Metric: Attribute-level F1 (%): the F1 of each target attribute computed over all instances, averaged over the category's attributes, for the next purchased baijiu item's attribute combination (price range, brand, alcohol content and packaging), predicted zero-shot from 100 users' one-year Kuaishou e-commerce interaction histories (clicks, add-to-cart and purchases with titles, selling points and price tiers, up to about 340K tokens); ground truth from verified purchases after a shopping festival cut-off; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 1.8 | 65.12 | #136 |
| 2 | DeepSeek V3.2 | 63.13 | #198 |
| 3 | Claude Sonnet 4.5 | 63.11 | #138 |
| 4 | Gemini 2.5 Pro | 62.16 | #145 |
| 5 | Gemini 2.5 Flash | 59.92 | #237 |
| 6 | GPT-5.2 Instant | 59.34 | #205 |
| 7 | GLM-4.6 | 58.55 | #246 |
| 8 | MiniMax-M2 | 56.33 | #307 |
| 9 | DeepSeek R1 | 55.27 | #245 |
| 10 | MiniMax-M2.1 | 54.08 | #283 |
| 11 | Qwen 3 235B A22B 2507 Instruct | 53.54 | #291 |
| 12 | GLM-4.5 | 53.35 | #265 |
| 13 | Qwen 3 Max (Preview) | 51.46 | #224 |
| 14 | Qwen 3 30B A3B 2507 (Thinking) | 47.87 | #366 (Qwen 3 30B A3B 2507) |
| 15 | Kimi K2 | 37.93 | #236 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=alpbench-baijiu-attribute-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.