Benchmark Almanac

SuperCLUE-Industry

GPT-4 Turbo (Jan 2024) 74.8 leads since March 2024
Not in model cards

Models answer multi-turn questions about industrial work in Chinese. A judging model applies task-specific criteria.

Tasks include diagnosing problems on an assembly line and retrieving records from production data.

Made by
SuperCLUE team
Released
March 2024
Kind
Tasks from real jobs
Level
University
Scored
Graded by a model
Answers
Open-ended
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Multi-turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
February 2024
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 6 models we track

GPT-4 Turbo (Jan 2024) leads with 74.8 among models released by February 2024 GPT-4 Turbo (Jan 2024) leads with 74.8 among models released by February 2024

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 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-4 Turbo (Jan 2024) API 74.8
  2. 2 GPT-4 Jun 2023, API 66.6
  3. 3 奇智孔明AInno-15B-1128 API 65.2
  4. 4 Qwen1.5-14B-Chat API 64.8
  5. 5 讯飞星火V3.0 API 63.8
  6. 6 GPT-3.5 Turbo Jan 2024, API 63.6
  7. 7 Baichuan2-13B-Chat 模型 61.8
  8. 8 ChatGLM-Turbo API 59.8
  9. 9 文心一言3.5 API 54.2
  10. 10 ChatGLM3-6B 模型 52.8
  11. 11 Chinese_Alpaca2_13B 模型 51.4
  12. 12 Llama_2_13B_Chat 模型 50.0

Source: Official SuperCLUE-Industry leaderboard

#EntryScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 74.8 API Jan 2024 Official leaderboard
2 GPT-4 Jun 2023 66.6 API Jun 2023 Official leaderboard
3 奇智孔明AInno-15B-1128 65.2 API Official leaderboard
4 Qwen1.5-14B-Chat 64.8 API Feb 2024 Official leaderboard
5 讯飞星火V3.0 63.8 API Official leaderboard
6 GPT-3.5 Turbo Jan 2024 63.6 API Jan 2024 Official leaderboard
7 Baichuan2-13B-Chat 61.8 模型 Sep 2023 Official leaderboard
8 ChatGLM-Turbo 59.8 API Official leaderboard
9 文心一言3.5 54.2 API Official leaderboard
10 ChatGLM3-6B 52.8 模型 Oct 2023 Official leaderboard
11 Chinese_Alpaca2_13B 51.4 模型 Official leaderboard
12 Llama_2_13B_Chat 50.0 模型 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 74.8 API Jan 2024 Official leaderboard
2 GPT-4 Jun 2023 66.6 API Jun 2023 Official leaderboard
3 Qwen1.5-14B-Chat 64.8 API Feb 2024 Official leaderboard
4 GPT-3.5 Turbo Jan 2024 63.6 API Jan 2024 Official leaderboard
5 Baichuan2-13B-Chat 61.8 模型 Sep 2023 Official leaderboard
6 ChatGLM3-6B 52.8 模型 Oct 2023 Official leaderboard

Rankings by part

We read 8 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 基础能力, 工业常规问答 and 工业理解计算. GPT-4 Turbo (Jan 2024) leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

基础能力

6 models we track have a score here.

  1. 1 GPT-4 Turbo (Jan 2024) 74.2
  2. 2 GPT-4 Jun 2023 65.5
  3. 3 Qwen1.5-14B-Chat 61.8
  4. 4 GPT-3.5 Turbo Jan 2024 61.5
  5. 5 Baichuan2-13B-Chat 60.1
  6. 6 ChatGLM3-6B 50.3

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 Mar 2024

Source: Official SuperCLUE-Industry 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
50.0 55.0 60.0 65.0 70.0 75.0 2023 2024 50.0 55.0 60.0 65.0 70.0 75.0 2023 2024

Source: Official SuperCLUE-Industry 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 Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

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 (12 entries).
  • Pass Models scored 6 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Qwen1.5-14B-Chat.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 6 rows for models we track and 6 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