Benchmark Almanac

SuperCLUE-DeepSearch

ChatGPT agent 74.3 leads since July 2025
Not in model cards

Agents search for information to answer Chinese research questions.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Questions that need search
Level
University
Scored
Settled by events
Answers
Agent task
Measures
Capability
Language
Chinese
In and out
Text → Actions, Text
Interaction
Agentic
Environment
Browser
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
Gemini 3 Pro #56 on the capability index
Last model added
November 2025
Scores refreshed
November 20th, 2026
24
Entries on its own leaderboard, 8 models we track

ChatGPT agent leads with 74.3 among models released by November 2025 ChatGPT agent leads with 74.3 among models released by November 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. This view shows only models we track, each at its best.

The newest model with a score here came out in November 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 ChatGPT agent 智能体 / 网页 74.3
  2. 2 openPangu-R-72B 模型 / API 73.3
  3. 3 GPT-5.1 high / 模型 / 网页 / 进阶思考+搜索 70.5
  4. 4 Gemini 3 Pro 模型 / 网页 / Google Search 70.5
  5. 5 Manus 1.5 智能体 / 网页 69.5
  6. 6 GPT-5 high / 模型 / 网页 / 进阶思考+搜索 67.6
  7. 7 Genspark 智能体 / 网页 62.9
  8. 8 Kimi K2 Thinking 模型 / API 61.0
  9. 9 Grok DeepSearch 智能体 / 网页 / 专家模式 59.0
  10. 10 Qwen3-Max 模型 / 网页 59.0
  11. 11 Kimi K2 Thinking Turbo 模型 / 网页 59.0
  12. 12 MiniMax Agent 智能体 / 网页 / 专业版 58.1
  13. 13 豆包 深入研究 智能体 / 客户端 57.1
  14. 14 阶跃 深入研究 智能体 / 网页 54.3
  15. 15 扣子空间 智能体 / 网页 46.7
  16. 16 秘塔AI搜索 智能体 / 网页 / 深度研究+快思考 46.7
  17. 17 元宝 模型 / 网页 / Hunyuan+T1·深度思考+手动联网 45.7
  18. 18 夸克 智能体 / 客户端 / 深度搜索模式 45.7
  19. 19 Kimi-K2-Turbo 模型 / 网页 43.8
  20. 20 天工 Agent 智能体 / 网页 / 通用模式 42.9
  21. 21 豆包 模型 / 网页 42.9
  22. 22 Qwen 深入研究 智能体 / 网页 / 高级模式 41.0
  23. 23 心流AI助手 智能体 / 网页 / AI搜索-深度搜索 38.1
  24. 24 DeepSeek-V3.2-Exp 模型 / 网页 / 深度搜索+联网 37.1

Source: Official SuperCLUE-DeepSearch leaderboard

#EntryScoreSettingDateSource
1 ChatGPT agent 74.3 智能体 / 网页 Jul 2025 Official leaderboard
2 openPangu-R-72B 73.3 模型 / API Official leaderboard
3 GPT-5.1 70.5 high / 模型 / 网页 / 进阶思考+搜索 Nov 2025 Official leaderboard
4 Gemini 3 Pro 70.5 模型 / 网页 / Google Search Nov 2025 Official leaderboard
5 Manus 1.5 69.5 智能体 / 网页 Official leaderboard
6 GPT-5 67.6 high / 模型 / 网页 / 进阶思考+搜索 Aug 2025 Official leaderboard
7 Genspark 62.9 智能体 / 网页 Official leaderboard
8 Kimi K2 Thinking 61.0 模型 / API Nov 2025 Official leaderboard
9 Grok DeepSearch 59.0 智能体 / 网页 / 专家模式 Official leaderboard
10 Qwen3-Max 59.0 模型 / 网页 Sep 2025 Official leaderboard
11 Kimi K2 Thinking Turbo 59.0 模型 / 网页 Nov 2025 Official leaderboard
12 MiniMax Agent 58.1 智能体 / 网页 / 专业版 Official leaderboard
13 豆包 深入研究 57.1 智能体 / 客户端 Official leaderboard
14 阶跃 深入研究 54.3 智能体 / 网页 Official leaderboard
15 扣子空间 46.7 智能体 / 网页 Official leaderboard
16 秘塔AI搜索 46.7 智能体 / 网页 / 深度研究+快思考 Official leaderboard
17 元宝 45.7 模型 / 网页 / Hunyuan+T1·深度思考+手动联网 Official leaderboard
18 夸克 45.7 智能体 / 客户端 / 深度搜索模式 Official leaderboard
19 Kimi-K2-Turbo 43.8 模型 / 网页 Official leaderboard
20 天工 Agent 42.9 智能体 / 网页 / 通用模式 Official leaderboard
21 豆包 42.9 模型 / 网页 Official leaderboard
22 Qwen 深入研究 41.0 智能体 / 网页 / 高级模式 Official leaderboard
23 心流AI助手 38.1 智能体 / 网页 / AI搜索-深度搜索 Official leaderboard
24 DeepSeek-V3.2-Exp 37.1 模型 / 网页 / 深度搜索+联网 Sep 2025 Official leaderboard
#ModelScoreSettingDateSource
1 ChatGPT agent 74.3 智能体 / 网页 Jul 2025 Official leaderboard
2 GPT-5.1 70.5 high / 模型 / 网页 / 进阶思考+搜索 Nov 2025 Official leaderboard
3 Gemini 3 Pro 70.5 模型 / 网页 / Google Search Nov 2025 Official leaderboard
4 GPT-5 67.6 high / 模型 / 网页 / 进阶思考+搜索 Aug 2025 Official leaderboard
5 Kimi K2 Thinking 61.0 模型 / API Nov 2025 Official leaderboard
6 Qwen3-Max 59.0 模型 / 网页 Sep 2025 Official leaderboard
7 Kimi K2 Thinking Turbo 59.0 模型 / 网页 Nov 2025 Official leaderboard
8 DeepSeek-V3.2-Exp 37.1 模型 / 网页 / 深度搜索+联网 Sep 2025 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 人文社科, 工程技术 and 自然科学. ChatGPT agent leads 5 of them, and GPT-5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

人文社科

8 models we track have a score here.

  1. 1 ChatGPT agent 73.6
  2. 2 Gemini 3 Pro ↑1 73.6
  3. 3 GPT-5.1 ↓1 67.9
  4. 4 Qwen3-Max ↑2 64.2
  5. 5 GPT-5 ↓1 60.4
  6. 6 Kimi K2 Thinking ↓1 58.5
  7. 7 Kimi K2 Thinking Turbo 54.7
  8. 8 DeepSeek-V3.2-Exp 34.0

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Nov 2025

Source: Official SuperCLUE-DeepSearch 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
30.0 40.0 50.0 60.0 70.0 80.0 2026 30.0 40.0 50.0 60.0 70.0 80.0 2026

Source: Official SuperCLUE-DeepSearch 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

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 (24 entries).
  • Pass Models scored 8 models we track, plus 16 other entries on its leaderboard.
  • Warning Newest score The newest came 12 months ago, in November 2025, for Gemini 3 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Pro (#56).
  • 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 16 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