SuperCLUE-Agent Scenario
Agents complete tasks drawn from Chinese application scenarios.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- General assistants
- Level
- University
- Scored
- Settled by events
- Answers
- Agent task
- Measures
- Capability
- Language
- Chinese
- Interaction
- Agentic
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
-
DeepSeek V4.1 Flash 1017 #23 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
DeepSeek V4.1 Flash 1017 leads with 96.6 DeepSeek V4.1 Flash 1017 leads with 96.6
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.
- 1
DeepSeek V4.1 Flash 1017 max 96.6
- 2 GLM-5.3-Flash max 96.6
- 3 Xing4.1-Preview 96.2
- 4
Tencent Hy3 high 96.2
- 5
Qwen3.7-Plus thinking 96.1
- 6
DeepSeek V4 Flash 0731 max 94.6
Source: Official SuperCLUE-Agent Scenario leaderboard
- 1
DeepSeek V4.1 Flash 1017 max 96.6
- 2 GLM-5.3-Flash max 96.6
- 3
Tencent Hy3 high 96.2
- 4
Qwen3.7-Plus thinking 96.1
- 5
DeepSeek V4 Flash 0731 max 94.6
Source: Official SuperCLUE-Agent Scenario leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 96.6 | max | Oct 2026 | Official leaderboard |
| 2 | GLM-5.3-Flash | 96.6 | max | Aug 2026 | Official leaderboard |
| 3 | Xing4.1-Preview | 96.2 | Official leaderboard | ||
| 4 | | 96.2 | high | Jul 2026 | Official leaderboard |
| 5 | | 96.1 | thinking | Jun 2026 | Official leaderboard |
| 6 | | 94.6 | max | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 96.6 | max | Oct 2026 | Official leaderboard |
| 2 | GLM-5.3-Flash | 96.6 | max | Aug 2026 | Official leaderboard |
| 3 | | 96.2 | high | Jul 2026 | Official leaderboard |
| 4 | | 96.1 | thinking | Jun 2026 | Official leaderboard |
| 5 | | 94.6 | max | Jul 2026 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 编码能力, 记忆能力 and 内容创作. Qwen3.7-Plus leads 3 of them, and Tencent Hy3 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
编码能力
5 models we track have a score here.
- 1
Qwen3.7-Plus ↑3 98.6
- 2
Tencent Hy3 ↑1 98.6
- 3
DeepSeek V4 Flash 0731 ↑2 98.6
- 4 GLM-5.3-Flash ↓2 98.6
- 5
DeepSeek V4.1 Flash 1017 ↓4 98.6
记忆能力
5 models we track have a score here.
- 1
Qwen3.7-Plus ↑3 90.0
- 2 GLM-5.3-Flash 90.0
- 3
DeepSeek V4.1 Flash 1017 ↓2 90.0
- 4
Tencent Hy3 ↓1 85.0
- 5
DeepSeek V4 Flash 0731 68.8
内容创作
5 models we track have a score here.
- 1
Tencent Hy3 ↑2 100.0
- 2
DeepSeek V4 Flash 0731 ↑3 100.0
- 3 GLM-5.3-Flash ↓1 100.0
- 4
DeepSeek V4.1 Flash 1017 ↓3 98.4
- 5
Qwen3.7-Plus ↓1 98.2
数据处理
5 models we track have a score here.
- 1
Tencent Hy3 ↑2 98.2
- 2
DeepSeek V4.1 Flash 1017 ↓1 98.2
- 3
DeepSeek V4 Flash 0731 ↑2 97.3
- 4 GLM-5.3-Flash ↓2 97.3
- 5
Qwen3.7-Plus ↓1 95.7
研究分析
5 models we track have a score here.
- 1
Qwen3.7-Plus ↑3 94.7
- 2
DeepSeek V4.1 Flash 1017 ↓1 94.6
- 3 GLM-5.3-Flash ↓1 93.9
- 4
DeepSeek V4 Flash 0731 ↑1 93.6
- 5
Tencent Hy3 ↓2 93.3
4 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-Agent Scenario 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-Agent Scenario 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 Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Neon 56.3%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state.
Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%
Data audit
8 of 9 checks pass, 1 warning. 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 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (6 entries).
- Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from October 2026, for DeepSeek V4.1 Flash 1017.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek V4.1 Flash 1017 (#23).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 5 rows for models we track and 1 other entry 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.