ALPBench - Fishing Rods (Profile F1): leaderboard
Metric: Profile-level F1 (%): the harmonic mean of the shares of predicted and of ground-truth attribute combinations that match exactly (every attribute right), for the next purchased fishing rods item's attribute combination (price range, brand, material and rod action), 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 2028. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 1.8 | 18.33 | #136 |
| 2 | Qwen 3 Max (Preview) | 18.33 | #224 |
| 3 | Gemini 2.5 Pro | 18.17 | #145 |
| 4 | Gemini 2.5 Flash | 16.81 | #237 |
| 5 | DeepSeek R1 | 16.33 | #245 |
| 6 | MiniMax-M2 | 15.17 | #307 |
| 7 | DeepSeek V3.2 | 14.83 | #198 |
| 8 | Claude Sonnet 4.5 | 13.77 | #138 |
| 9 | MiniMax-M2.1 | 13.27 | #283 |
| 10 | GLM-4.5 | 12.5 | #265 |
| 11 | GPT-5.2 Instant | 12.23 | #205 |
| 12 | Kimi K2 | 11.67 | #236 |
| 13 | Qwen 3 30B A3B 2507 (Thinking) | 10.67 | #366 (Qwen 3 30B A3B 2507) |
| 14 | Qwen 3 235B A22B 2507 Instruct | 9.33 | #291 |
| 15 | GLM-4.6 | 9.17 | #246 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=alpbench-fishing-rods-profile-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.