SuperCLUE-Mkt
Models complete tasks in advertising and marketing.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- Running a business
- Level
- University
- Scored
- Graded by people
- Answers
- Open-ended
- Measures
- Capability
- Language
- Chinese
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- Law and finance
- Strongest model tested
-
DeepSeek-V3.2 #91 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
Tec-Chi-Think-1.0-32B tops the leaderboard with 85.8 DeepSeek-V3.2 leads with 85.7 among models released by December 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is DeepSeek-V3.2, at 85.7. This view shows only models we track, each at its best.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Tec-Chi-Think-1.0-32B API 85.8
- 2
DeepSeek-V3.2 API 85.7
- 3 Spark-X1.5 API 83.4
- 4
Qwen3-32B Thinking / API 82.4
- 5 GLM-4.6 API 80.0
- 6 GPT-5 nano API 78.6
- 7
Gemma 3 27B API 78.2
- 8 gpt-oss-120b API 77.2
- 9 GLM-4-32B-0414 API 74.3
- 10
DeepSeek-R1-Distill-Qwen-32B API 69.8
- 11
InternLM3-8B-Instruct API 64.5
- 12 Llama-3.1-70B-Instruct API 52.8
Source: Official SuperCLUE-Mkt leaderboard
- 1
DeepSeek-V3.2 API 85.7
- 2
Qwen3-32B Thinking / API 82.4
- 3 GLM-4.6 API 80.0
- 4 GPT-5 nano API 78.6
- 5
Gemma 3 27B API 78.2
- 6 gpt-oss-120b API 77.2
- 7
DeepSeek-R1-Distill-Qwen-32B API 69.8
- 8
InternLM3-8B-Instruct API 64.5
Source: Official SuperCLUE-Mkt leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Tec-Chi-Think-1.0-32B | 85.8 | API | Official leaderboard | |
| 2 | | 85.7 | API | Dec 2025 | Official leaderboard |
| 3 | Spark-X1.5 | 83.4 | API | Official leaderboard | |
| 4 | | 82.4 | Thinking / API | Apr 2025 | Official leaderboard |
| 5 | GLM-4.6 | 80.0 | API | Sep 2025 | Official leaderboard |
| 6 | GPT-5 nano | 78.6 | API | Aug 2025 | Official leaderboard |
| 7 | | 78.2 | API | Mar 2025 | Official leaderboard |
| 8 | gpt-oss-120b | 77.2 | API | Aug 2025 | Official leaderboard |
| 9 | GLM-4-32B-0414 | 74.3 | API | Official leaderboard | |
| 10 | | 69.8 | API | Jan 2025 | Official leaderboard |
| 11 | | 64.5 | API | Jan 2025 | Official leaderboard |
| 12 | Llama-3.1-70B-Instruct | 52.8 | API | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 85.7 | API | Dec 2025 | Official leaderboard |
| 2 | | 82.4 | Thinking / API | Apr 2025 | Official leaderboard |
| 3 | GLM-4.6 | 80.0 | API | Sep 2025 | Official leaderboard |
| 4 | GPT-5 nano | 78.6 | API | Aug 2025 | Official leaderboard |
| 5 | | 78.2 | API | Mar 2025 | Official leaderboard |
| 6 | gpt-oss-120b | 77.2 | API | Aug 2025 | Official leaderboard |
| 7 | | 69.8 | API | Jan 2025 | Official leaderboard |
| 8 | | 64.5 | API | Jan 2025 | Official leaderboard |
Rankings by part
We read 15 parts from the benchmark’s own leaderboard in 4 groups: 市场洞察, 投放策略, 创意生产 and 合规评估. Each ranks models on one part of the test. DeepSeek-V3.2 leads 12 of them, and Qwen3-32B leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.
市场洞察
8 models we track have a score here.
- 1
DeepSeek-V3.2 88.1
- 2
Qwen3-32B 80.9
- 3 GPT-5 nano ↑1 80.4
- 4 GLM-4.6 ↓1 80.1
- 5
Gemma 3 27B 78.0
- 6 gpt-oss-120b 77.3
- 7
DeepSeek-R1-Distill-Qwen-32B 74.2
- 8
InternLM3-8B-Instruct 68.8
投放策略
8 models we track have a score here.
- 1
DeepSeek-V3.2 89.7
- 2
Qwen3-32B 85.6
- 3 GLM-4.6 79.3
- 4 GPT-5 nano 78.5
- 5
Gemma 3 27B 76.2
- 6 gpt-oss-120b 75.4
- 7
DeepSeek-R1-Distill-Qwen-32B 66.2
- 8
InternLM3-8B-Instruct 59.1
创意生产
8 models we track have a score here.
- 1
Qwen3-32B ↑1 75.9
- 2 GLM-4.6 ↑1 73.5
- 3
DeepSeek-V3.2 ↓2 72.8
- 4 gpt-oss-120b ↑2 71.7
- 5
Gemma 3 27B 70.8
- 6 GPT-5 nano ↓2 66.5
- 7
DeepSeek-R1-Distill-Qwen-32B 61.7
- 8
InternLM3-8B-Instruct 55.2
合规评估
8 models we track have a score here.
- 1
DeepSeek-V3.2 92.3
- 2 GPT-5 nano ↑2 88.9
- 3
Gemma 3 27B ↑2 87.6
- 4
Qwen3-32B ↓2 87.2
- 5 GLM-4.6 ↓2 86.8
- 6 gpt-oss-120b 84.3
- 7
DeepSeek-R1-Distill-Qwen-32B 77.3
- 8
InternLM3-8B-Instruct 74.8
产品受众匹配
8 models we track have a score here.
- 1
DeepSeek-V3.2 97.1
- 2 gpt-oss-120b ↑4 94.1
- 3
Qwen3-32B ↓1 91.2
- 4 GPT-5 nano 91.2
- 5 GLM-4.6 ↓2 91.2
- 6
DeepSeek-R1-Distill-Qwen-32B ↑1 85.3
- 7
Gemma 3 27B ↓2 82.3
- 8
InternLM3-8B-Instruct 76.5
产品理解
8 models we track have a score here.
- 1
DeepSeek-V3.2 87.4
- 2 GLM-4.6 ↑1 81.7
- 3
Gemma 3 27B ↑2 80.0
- 4
Qwen3-32B ↓2 77.5
- 5 gpt-oss-120b ↑1 77.0
- 6 GPT-5 nano ↓2 75.2
- 7
DeepSeek-R1-Distill-Qwen-32B 69.7
- 8
InternLM3-8B-Instruct 67.7
目标市场分析
8 models we track have a score here.
- 1
DeepSeek-V3.2 79.6
- 2 GPT-5 nano ↑2 74.5
- 3
Qwen3-32B ↓1 73.7
- 4
Gemma 3 27B ↑1 71.6
- 5
DeepSeek-R1-Distill-Qwen-32B ↑2 67.3
- 6 GLM-4.6 ↓3 67.2
- 7
InternLM3-8B-Instruct ↑1 62.0
- 8 gpt-oss-120b ↓2 60.3
品牌定位策略
8 models we track have a score here.
- 1
DeepSeek-V3.2 90.8
- 2
Qwen3-32B 89.3
- 3 GLM-4.6 83.4
- 4
Gemma 3 27B ↑1 79.9
- 5
DeepSeek-R1-Distill-Qwen-32B ↑2 77.5
- 6 gpt-oss-120b 77.1
- 7 GPT-5 nano ↓3 75.7
- 8
InternLM3-8B-Instruct 63.9
市场进入策略
8 models we track have a score here.
- 1
DeepSeek-V3.2 89.6
- 2
Qwen3-32B 85.1
- 3 GPT-5 nano ↑1 79.8
- 4 gpt-oss-120b ↑2 78.0
- 5 GLM-4.6 ↓2 74.2
- 6
Gemma 3 27B ↓1 74.1
- 7
DeepSeek-R1-Distill-Qwen-32B 59.9
- 8
InternLM3-8B-Instruct 53.7
平台差异化
8 models we track have a score here.
- 1
DeepSeek-V3.2 88.5
- 2
Qwen3-32B 82.3
- 3 GLM-4.6 80.5
- 4 GPT-5 nano 79.9
- 5
Gemma 3 27B 74.4
- 6 gpt-oss-120b 70.8
- 7
DeepSeek-R1-Distill-Qwen-32B 60.9
- 8
InternLM3-8B-Instruct 59.9
文案生成
8 models we track have a score here.
- 1
Qwen3-32B ↑1 80.6
- 2
Gemma 3 27B ↑3 74.1
- 3
DeepSeek-V3.2 ↓2 72.3
- 4 gpt-oss-120b ↑2 72.0
- 5 GLM-4.6 ↓2 71.3
- 6 GPT-5 nano ↓2 68.0
- 7
DeepSeek-R1-Distill-Qwen-32B 61.6
- 8
InternLM3-8B-Instruct 56.4
爆品模仿
8 models we track have a score here.
- 1
Qwen3-32B ↑1 71.8
- 2 GLM-4.6 ↑1 71.1
- 3 gpt-oss-120b ↑3 66.5
- 4
DeepSeek-V3.2 ↓3 65.9
- 5
Gemma 3 27B 61.2
- 6
DeepSeek-R1-Distill-Qwen-32B ↑1 56.3
- 7 GPT-5 nano ↓3 55.2
- 8
InternLM3-8B-Instruct 50.6
脚本生成
8 models we track have a score here.
- 1
DeepSeek-V3.2 78.4
- 2 GLM-4.6 ↑1 77.0
- 3
Gemma 3 27B ↑2 75.5
- 4
Qwen3-32B ↓2 75.5
- 5 gpt-oss-120b ↑1 75.5
- 6 GPT-5 nano ↓2 73.9
- 7
DeepSeek-R1-Distill-Qwen-32B 65.8
- 8
InternLM3-8B-Instruct 57.9
合规检查
8 models we track have a score here.
- 1
DeepSeek-V3.2 93.2
- 2 GPT-5 nano ↑2 89.8
- 3
Gemma 3 27B ↑2 89.2
- 4 GLM-4.6 ↓1 87.9
- 5 gpt-oss-120b ↑1 84.7
- 6
Qwen3-32B ↓4 84.2
- 7
DeepSeek-R1-Distill-Qwen-32B 81.5
- 8
InternLM3-8B-Instruct 77.7
风险预审
8 models we track have a score here.
- 1
DeepSeek-V3.2 91.7
- 2
Qwen3-32B 89.5
- 3 GPT-5 nano ↑1 88.2
- 4
Gemma 3 27B ↑1 86.3
- 5 GLM-4.6 ↓2 86.0
- 6 gpt-oss-120b 84.0
- 7
DeepSeek-R1-Distill-Qwen-32B 73.9
- 8
InternLM3-8B-Instruct 72.4
5 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SuperCLUE-Mkt leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SuperCLUE-Mkt leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9%
- GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
Data audit
7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (12 entries).
- Pass Models scored 8 models we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 11 months ago, in December 2025, for DeepSeek-V3.2.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-V3.2 (#91).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 8 rows for models we track and 4 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.