SuperCLUE-Mkt - Compliance Assessment: leaderboard
SuperCLUE is the Chinese-language evaluation programme run by CLUE; its specialised boards each cover one professional domain and are graded by the organisers rather than self-reported. This board covers marketing: judging whether a campaign clears advertising compliance rules.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 92.34 | #205 (DeepSeek V3.2) |
| 2 | Spark X1.5 | 90.83 | #390 |
| 3 | GPT-5 Nano | 88.88 | #425 |
| 4 | Gemma 3 27B (IT) | 87.57 | #523 |
| 5 | Qwen 3 32B (Thinking) | 87.22 | #443 (Qwen 3 32B) |
| 6 | GLM-4.6 | 86.84 | #252 |
| 7 | GLM-4 32B (0414) | 84.88 | #533 |
| 8 | GPT-OSS-120B | 84.31 | #341 |
| 9 | DeepSeek R1 Distill Qwen 32B | 77.27 | #655 |
| 10 | InternLM3-8B-Instruct | 74.76 | #867 |
| 11 | Llama 3.1 70B Instruct | 56.89 | #561 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-mkt-compliance-assessment · How It Works · Data refreshed daily, snapshot 2026-10-20.