Benchmark Almanac

SuperCLUE-Mkt

Tec-Chi-Think-1.0-32B 85.8 tops its leaderboard DeepSeek-V3.2 85.7 leads the models we track
Not in model cards

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
In and out
Text → Text
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
12
Entries on its own leaderboard, 8 models we track

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:

  1. 1 Tec-Chi-Think-1.0-32B API 85.8
  2. 2 DeepSeek-V3.2 API 85.7
  3. 3 Spark-X1.5 API 83.4
  4. 4 Qwen3-32B Thinking / API 82.4
  5. 5 GLM-4.6 API 80.0
  6. 6 GPT-5 nano API 78.6
  7. 7 Gemma 3 27B API 78.2
  8. 8 gpt-oss-120b API 77.2
  9. 9 GLM-4-32B-0414 API 74.3
  10. 10 DeepSeek-R1-Distill-Qwen-32B API 69.8
  11. 11 InternLM3-8B-Instruct API 64.5
  12. 12 Llama-3.1-70B-Instruct API 52.8

Source: Official SuperCLUE-Mkt leaderboard

#EntryScoreSettingDateSource
1 Tec-Chi-Think-1.0-32B 85.8 API Official leaderboard
2 DeepSeek-V3.2 85.7 API Dec 2025 Official leaderboard
3 Spark-X1.5 83.4 API Official leaderboard
4 Qwen3-32B 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 Gemma 3 27B 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 DeepSeek-R1-Distill-Qwen-32B 69.8 API Jan 2025 Official leaderboard
11 InternLM3-8B-Instruct 64.5 API Jan 2025 Official leaderboard
12 Llama-3.1-70B-Instruct 52.8 API Official leaderboard
#ModelScoreSettingDateSource
1 DeepSeek-V3.2 85.7 API Dec 2025 Official leaderboard
2 Qwen3-32B 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 Gemma 3 27B 78.2 API Mar 2025 Official leaderboard
6 gpt-oss-120b 77.2 API Aug 2025 Official leaderboard
7 DeepSeek-R1-Distill-Qwen-32B 69.8 API Jan 2025 Official leaderboard
8 InternLM3-8B-Instruct 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. 1 DeepSeek-V3.2 88.1
  2. 2 Qwen3-32B 80.9
  3. 3 GPT-5 nano ↑1 80.4
  4. 4 GLM-4.6 ↓1 80.1
  5. 5 Gemma 3 27B 78.0
  6. 6 gpt-oss-120b 77.3
  7. 7 DeepSeek-R1-Distill-Qwen-32B 74.2
  8. 8 InternLM3-8B-Instruct 68.8

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.

Shanghai AI Lab DeepSeek Google DeepMind Qwen
Own leaderboard Not tested since Dec 2025

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
60.0 70.0 80.0 90.0 2025 2026 60.0 70.0 80.0 90.0 2025 2026

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

All 210 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.

How we check