HSCodeComp - 8-digit: leaderboard
Metric: Exact Match Accuracy (%). Source: arxiv.org. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 40.98 |
| 2 | Gemini 2.5 Pro | 40.35 |
| 3 | GPT-4o | 30.06 |
| 4 | Kimi K2 | 24.53 |
| 5 | Claude Sonnet 4 | 23.58 |
| 6 | DeepSeek V3 | 17.25 |
| 7 | DeepSeek R1 | 16.77 |
| 8 | Qwen Max | 11.23 |
| 9 | O3 Mini | 6.65 |
| 10 | Qwen 3 235B A22B | 6.01 |
| 11 | QwQ-32B | 1.42 |
| 12 | Qwen 2.5 72B | 1.42 |
| 13 | Qwen 3 32B | 1.27 |
Interactive version: theaggregate.ai/benchmark?slug=hscodecomp-8-digit · How It Works · Data refreshed daily, snapshot 2026-09-05.