ALPBench - Cell Phones (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 cell phones item's attribute combination (price range, brand, wireless charging, battery capacity, screen size, rear camera setup, NFC support and charging power), 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 December 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 Instant | 46.61 | #205 |
| 2 | Seed 1.8 | 45.78 | #136 |
| 3 | Gemini 2.5 Pro | 45.08 | #145 |
| 4 | Claude Sonnet 4.5 | 43.35 | #138 |
| 5 | MiniMax-M2.1 | 42.32 | #283 |
| 6 | Qwen 3 Max (Preview) | 42.06 | #224 |
| 7 | Gemini 2.5 Flash | 42.03 | #237 |
| 8 | Qwen 3 235B A22B 2507 Instruct | 41.86 | #291 |
| 9 | MiniMax-M2 | 40.71 | #307 |
| 10 | DeepSeek V3.2 | 40.67 | #198 |
| 11 | DeepSeek R1 | 38.58 | #245 |
| 12 | GLM-4.6 | 38.35 | #246 |
| 13 | Qwen 3 30B A3B 2507 (Thinking) | 37.1 | #366 (Qwen 3 30B A3B 2507) |
| 14 | GLM-4.5 | 37.1 | #265 |
| 15 | Kimi K2 | 36.56 | #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-cell-phones-attribute-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.