Benchmark Almanac

AgentCLUE

Claude 3.5 Sonnet (October 2024) 46.4 leads since October 2024
Not in model cards

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
In and out
Text → Actions
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
12
Entries on its own leaderboard, 10 models we track

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:

  1. 1 Claude 3.5 Sonnet (October 2024) API 46.4
  2. 2 GPT-4o Nov 2024, API 42.9
  3. 3 Gemini 2.0 Flash Feb 2025, API 36.6
  4. 4 Doubao-1.5-pro API 36.6
  5. 5 GPT-4o mini API 34.3
  6. 6 Moonshot-V1-128k API 31.2
  7. 7 Qwen2.5-72B API 30.1
  8. 8 GLM4-plus API 28.5
  9. 9 GLM-4-9B-Chat 模型 24.1
  10. 10 DeepSeek-V3 API 21.7
  11. 11 Qwen2.5-7B API 15.4
  12. 12 Llama 3.1-8B 模型 0.89

Source: Official AgentCLUE leaderboard

#EntryScoreSettingReleasedRun onSource
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 Gemini 2.0 Flash Feb 2025 36.6 API Feb 2025 Feb 2025 Official leaderboard
4 Doubao-1.5-pro 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 Qwen2.5-72B 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 DeepSeek-V3 21.7 API Dec 2024 Feb 2025 Official leaderboard
11 Qwen2.5-7B 15.4 API Sep 2024 Feb 2025 Official leaderboard
12 Llama 3.1-8B 0.89 模型 Jul 2024 Feb 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
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 Gemini 2.0 Flash Feb 2025 36.6 API Feb 2025 Feb 2025 Official leaderboard
4 Doubao-1.5-pro 36.6 API Jan 2025 Feb 2025 Official leaderboard
5 GPT-4o mini 34.3 API Jul 2024 Feb 2025 Official leaderboard
6 Qwen2.5-72B 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 DeepSeek-V3 21.7 API Dec 2024 Feb 2025 Official leaderboard
9 Qwen2.5-7B 15.4 API Sep 2024 Feb 2025 Official leaderboard
10 Llama 3.1-8B 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. 1 Claude 3.5 Sonnet (October 2024) 64.3
  2. 2 GPT-4o Nov 2024 64.0
  3. 3 Doubao-1.5-pro ↑1 53.6
  4. 4 Gemini 2.0 Flash Feb 2025 ↓1 50.0
  5. 5 Qwen2.5-72B ↑1 46.4
  6. 6 GPT-4o mini ↓1 46.1
  7. 7 GLM-4-9B-Chat 42.9
  8. 8 DeepSeek-V3 39.3
  9. 9 Qwen2.5-7B 25.0
  10. 10 Llama 3.1-8B 3.57

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.

Z.ai OpenAI Anthropic
Own leaderboard Not tested since Feb 2025

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 10.0 20.0 30.0 40.0 50.0 2024 2025 0.00 10.0 20.0 30.0 40.0 50.0 2024 2025

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

All 265 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.

How we check