Benchmark Almanac

SuperCLUE-Agent Scenario

DeepSeek V4.1 Flash 1017 96.6 leads since October 2026
Not in model cards

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
In and out
Text → Actions, Text
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
6
Entries on its own leaderboard, 5 models we track

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. 1 DeepSeek V4.1 Flash 1017 max 96.6
  2. 2 GLM-5.3-Flash max 96.6
  3. 3 Xing4.1-Preview 96.2
  4. 4 Tencent Hy3 high 96.2
  5. 5 Qwen3.7-Plus thinking 96.1
  6. 6 DeepSeek V4 Flash 0731 max 94.6

Source: Official SuperCLUE-Agent Scenario leaderboard

#EntryScoreSettingDateSource
1 DeepSeek V4.1 Flash 1017 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 Tencent Hy3 96.2 high Jul 2026 Official leaderboard
5 Qwen3.7-Plus 96.1 thinking Jun 2026 Official leaderboard
6 DeepSeek V4 Flash 0731 94.6 max Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 DeepSeek V4.1 Flash 1017 96.6 max Oct 2026 Official leaderboard
2 GLM-5.3-Flash 96.6 max Aug 2026 Official leaderboard
3 Tencent Hy3 96.2 high Jul 2026 Official leaderboard
4 Qwen3.7-Plus 96.1 thinking Jun 2026 Official leaderboard
5 DeepSeek V4 Flash 0731 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. 1 Qwen3.7-Plus ↑3 98.6
  2. 2 Tencent Hy3 ↑1 98.6
  3. 3 DeepSeek V4 Flash 0731 ↑2 98.6
  4. 4 GLM-5.3-Flash ↓2 98.6
  5. 5 DeepSeek V4.1 Flash 1017 ↓4 98.6

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.

Qwen Tencent Z.ai DeepSeek
Own leaderboard 4 leaders

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
94.5 95.0 95.5 96.0 96.5 97.0 2026 94.5 95.0 95.5 96.0 96.5 97.0 2026

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

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

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.

How we check