ALPBench - Snacks (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 snacks item's attribute combination (price range, sugar content, flavor, storage, category and others), 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: Not forecast. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 1.8 | 31.1 | #136 |
| 2 | Gemini 2.5 Flash | 30.32 | #237 |
| 3 | Gemini 2.5 Pro | 29.93 | #145 |
| 4 | MiniMax-M2.1 | 29.28 | #283 |
| 5 | GPT-5.2 Instant | 28.27 | #205 |
| 6 | Qwen 3 Max (Preview) | 28.13 | #224 |
| 7 | MiniMax-M2 | 26.9 | #307 |
| 8 | Qwen 3 30B A3B 2507 (Thinking) | 24.67 | #366 (Qwen 3 30B A3B 2507) |
| 9 | Qwen 3 235B A22B 2507 Instruct | 21.29 | #291 |
| 10 | DeepSeek R1 | 20.75 | #245 |
| 11 | DeepSeek V3.2 | 20.37 | #198 |
| 12 | GLM-4.6 | 20.12 | #246 |
| 13 | GLM-4.5 | 18.79 | #265 |
| 14 | Claude Sonnet 4.5 | 17.23 | #138 |
| 15 | Kimi K2 | 8.54 | #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-snacks-attribute-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.