AgentCLUE
Agents execute tasks in Chinese.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- Apps and MCP servers
- Level
- University
- Scored
- Settled by events
- Answers
- Agent task
- Measures
- Capability
- Language
- Chinese
- Interaction
- Agentic
- Environment
- APIs and tools
- Run by
- A host
- In views
- Agents
- Strongest model tested
-
Gemini 2.0 Flash Feb 2025 #147 on the capability index
- Last model added
- February 2025
- Scores refreshed
- November 20th, 2026
Claude 3.5 Sonnet (October 2024) leads with 46.4 among models released by February 2025 Claude 3.5 Sonnet (October 2024) leads with 46.4 among models released by February 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 February 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 Claude 3.5 Sonnet (October 2024) API 46.4
- 2 GPT-4o Nov 2024, API 42.9
- 3
Gemini 2.0 Flash Feb 2025, API 36.6
- 4
Doubao-1.5-pro API 36.6
- 5 GPT-4o mini API 34.3
- 6 Moonshot-V1-128k API 31.2
- 7
Qwen2.5-72B API 30.1
- 8 GLM4-plus API 28.5
- 9 GLM-4-9B-Chat 模型 24.1
- 10
DeepSeek-V3 API 21.7
- 11
Qwen2.5-7B API 15.4
- 12
Llama 3.1-8B 模型 0.89
Source: Official AgentCLUE leaderboard
- 1 Claude 3.5 Sonnet (October 2024) API 46.4
- 2 GPT-4o Nov 2024, API 42.9
- 3
Gemini 2.0 Flash Feb 2025, API 36.6
- 4
Doubao-1.5-pro API 36.6
- 5 GPT-4o mini API 34.3
- 6
Qwen2.5-72B API 30.1
- 7 GLM-4-9B-Chat 模型 24.1
- 8
DeepSeek-V3 API 21.7
- 9
Qwen2.5-7B API 15.4
- 10
Llama 3.1-8B 模型 0.89
Source: Official AgentCLUE leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude 3.5 Sonnet (October 2024) | 46.4 | API | Oct 2024 | Feb 2025 | Official leaderboard |
| 2 | GPT-4o Nov 2024 | 42.9 | API | Nov 2024 | Feb 2025 | Official leaderboard |
| 3 | | 36.6 | API | Feb 2025 | Feb 2025 | Official leaderboard |
| 4 | | 36.6 | API | Jan 2025 | Feb 2025 | Official leaderboard |
| 5 | GPT-4o mini | 34.3 | API | Jul 2024 | Feb 2025 | Official leaderboard |
| 6 | Moonshot-V1-128k | 31.2 | API | Feb 2025 | Official leaderboard | |
| 7 | | 30.1 | API | Sep 2024 | Feb 2025 | Official leaderboard |
| 8 | GLM4-plus | 28.5 | API | Feb 2025 | Official leaderboard | |
| 9 | GLM-4-9B-Chat | 24.1 | 模型 | Jun 2024 | Feb 2025 | Official leaderboard |
| 10 | | 21.7 | API | Dec 2024 | Feb 2025 | Official leaderboard |
| 11 | | 15.4 | API | Sep 2024 | Feb 2025 | Official leaderboard |
| 12 | | 0.89 | 模型 | Jul 2024 | Feb 2025 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude 3.5 Sonnet (October 2024) | 46.4 | API | Oct 2024 | Feb 2025 | Official leaderboard |
| 2 | GPT-4o Nov 2024 | 42.9 | API | Nov 2024 | Feb 2025 | Official leaderboard |
| 3 | | 36.6 | API | Feb 2025 | Feb 2025 | Official leaderboard |
| 4 | | 36.6 | API | Jan 2025 | Feb 2025 | Official leaderboard |
| 5 | GPT-4o mini | 34.3 | API | Jul 2024 | Feb 2025 | Official leaderboard |
| 6 | | 30.1 | API | Sep 2024 | Feb 2025 | Official leaderboard |
| 7 | GLM-4-9B-Chat | 24.1 | 模型 | Jun 2024 | Feb 2025 | Official leaderboard |
| 8 | | 21.7 | API | Dec 2024 | Feb 2025 | Official leaderboard |
| 9 | | 15.4 | API | Sep 2024 | Feb 2025 | Official leaderboard |
| 10 | | 0.89 | 模型 | Jul 2024 | Feb 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 常规多轮对话, 函数缺失 and 参数缺失. Claude 3.5 Sonnet (October 2024) leads 3 of them, and GPT-4o mini leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
常规多轮对话
10 models we track have a score here.
- 1 Claude 3.5 Sonnet (October 2024) 64.3
- 2 GPT-4o Nov 2024 64.0
- 3
Doubao-1.5-pro ↑1 53.6
- 4
Gemini 2.0 Flash Feb 2025 ↓1 50.0
- 5
Qwen2.5-72B ↑1 46.4
- 6 GPT-4o mini ↓1 46.1
- 7 GLM-4-9B-Chat 42.9
- 8
DeepSeek-V3 39.3
- 9
Qwen2.5-7B 25.0
- 10
Llama 3.1-8B 3.57
函数缺失
10 models we track have a score here.
- 1 Claude 3.5 Sonnet (October 2024) 42.9
- 2 GPT-4o Nov 2024 34.6
- 3
Doubao-1.5-pro ↑1 28.6
- 4
Gemini 2.0 Flash Feb 2025 ↓1 28.6
- 5 GPT-4o mini 23.1
- 6
Qwen2.5-72B 14.3
- 7 GLM-4-9B-Chat 10.7
- 8
Qwen2.5-7B ↑1 10.7
- 9
DeepSeek-V3 ↓1 7.14
- 10
Llama 3.1-8B 0.00
参数缺失
10 models we track have a score here.
- 1 Claude 3.5 Sonnet (October 2024) 52.2
- 2
Gemini 2.0 Flash Feb 2025 ↑1 47.8
- 3
Doubao-1.5-pro ↑1 39.1
- 4 GPT-4o Nov 2024 ↓2 38.1
- 5
Qwen2.5-72B ↑1 34.8
- 6 GPT-4o mini ↓1 33.3
- 7 GLM-4-9B-Chat 30.4
- 8
DeepSeek-V3 26.1
- 9
Qwen2.5-7B 17.4
- 10
Llama 3.1-8B 0.00
长上下文干扰
10 models we track have a score here.
- 1 GPT-4o mini ↑4 34.8
- 2 GPT-4o Nov 2024 34.8
- 3 Claude 3.5 Sonnet (October 2024) ↓2 26.1
- 4
Qwen2.5-72B ↑2 25.0
- 5
Doubao-1.5-pro ↓1 25.0
- 6
Gemini 2.0 Flash Feb 2025 ↓3 20.0
- 7
DeepSeek-V3 ↑1 14.3
- 8 GLM-4-9B-Chat ↓1 12.5
- 9
Qwen2.5-7B 8.33
- 10
Llama 3.1-8B 0.00
3 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 AgentCLUE 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 AgentCLUE 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
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 10 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 21 months ago, in February 2025, for Gemini 2.0 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.0 Flash (#147).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 10 rows for models we track and 2 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.