SuperCLUE-Mkt - Market Insight: 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: reading a market from the supplied evidence.
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) | 88.12 | #205 (DeepSeek V3.2) |
| 2 | Spark X1.5 | 84.39 | #390 |
| 3 | Qwen 3 32B (Thinking) | 80.92 | #443 (Qwen 3 32B) |
| 4 | GPT-5 Nano | 80.41 | #425 |
| 5 | GLM-4.6 | 80.14 | #252 |
| 6 | Gemma 3 27B (IT) | 78.05 | #523 |
| 7 | GLM-4 32B (0414) | 77.74 | #533 |
| 8 | GPT-OSS-120B | 77.32 | #341 |
| 9 | DeepSeek R1 Distill Qwen 32B | 74.21 | #655 |
| 10 | InternLM3-8B-Instruct | 68.79 | #867 |
| 11 | Llama 3.1 70B Instruct | 54.88 | #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-market-insight · How It Works · Data refreshed daily, snapshot 2026-10-20.