Benchmark Almanac

SuperCLUE-Open

GPT-4 Jun 2023 94.6 leads since July 2023
Not in model cards

Models answer Chinese open-domain questions over multiple turns. The authors compare models across skill categories.

The authors report the open-domain score separately from objective questions and anonymous preference votes.

Made by
SuperCLUE team
Released
July 2023
Kind
Chat and instructions in many languages
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Measures
Preference
Risk
Privacy
Language
Chinese
In and out
Text, Code → Text, Code
Interaction
Multi-turn
Refresh
One fixed set
Run by
A host
Based on
SuperCLUE
In views
Content safety
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
January 2024
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 3 models we track

GPT-4 leads with 94.6 among models released by January 2024 GPT-4 leads with 94.6 among models released by January 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 January 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 Jun 2023 94.6
  2. 2 Claude-instant-v1 69.5
  3. 3 GPT-3.5 Turbo Jan 2024 66.7
  4. 4 MiniMax-abab5 57.9
  5. 5 文心一言(v2.0.4) 50.5
  6. 6 讯飞星火(v1.5) 48.9
  7. 7 ChatGLM-130B 42.5
  8. 8 chatglm2-6b 36.5
  9. 9 Qwen-7B-Chat 25.8
  10. 10 360智脑(4.0) 23.9
  11. 11 IDEA-姜子牙-13B 22.0
  12. 12 MOSS-16B 21.1
  13. 13 BELLE-13B 15.6
  14. 14 RWKV-world-7B 12.4
  15. 15 baichuan-7B 3.11

Source: Official SuperCLUE-Open leaderboard

Source: Official SuperCLUE-Open leaderboard

#EntryScoreSettingDateSource
1 GPT-4 Jun 2023 94.6 Jun 2023 Official leaderboard
2 Claude-instant-v1 closed weights 69.5 Official leaderboard
3 GPT-3.5 Turbo Jan 2024 66.7 Jan 2024 Official leaderboard
4 MiniMax-abab5 closed weights 57.9 Official leaderboard
5 文心一言(v2.0.4) closed weights 50.5 Official leaderboard
6 讯飞星火(v1.5) closed weights 48.9 Official leaderboard
7 ChatGLM-130B closed weights 42.5 Official leaderboard
8 chatglm2-6b 36.5 Jun 2023 Official leaderboard
9 Qwen-7B-Chat open weights 25.8 Official leaderboard
10 360智脑(4.0) closed weights 23.9 Official leaderboard
11 IDEA-姜子牙-13B open weights 22.0 Official leaderboard
12 MOSS-16B open weights 21.1 Official leaderboard
13 BELLE-13B open weights 15.6 Official leaderboard
14 RWKV-world-7B open weights 12.4 Official leaderboard
15 baichuan-7B open weights 3.11 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Jun 2023 94.6 Jun 2023 Official leaderboard
2 GPT-3.5 Turbo Jan 2024 66.7 Jan 2024 Official leaderboard
3 chatglm2-6b 36.5 Jun 2023 Official leaderboard

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 Jan 2024
GPT-4 94.6

Source: Official SuperCLUE-Open 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
20.0 40.0 60.0 80.0 100.0 2023 2024 20.0 40.0 60.0 80.0 100.0 2023 2024

Source: Official SuperCLUE-Open 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 Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

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 (15 entries).
  • Pass Models scored 3 models we track, plus 12 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in January 2024, for GPT-3.5 Turbo.
  • 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: 3 rows for models we track and 12 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