Benchmark Almanac

SuperCLUE-Role

GPT-4 Turbo (Jan 2024) 75.2 leads since April 2024
Not in model cards

Models portray characters in Chinese conversations. A judging model rates aspects of the portrayal against reference answers.

The rubric uses five-point scales for criteria such as the character’s language style.

Made by
SuperCLUE team
Released
April 2024
Kind
Chat and instructions in many languages
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Multi-turn
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, 7 models we track

GPT-4 Turbo (Jan 2024) leads with 75.2 among models released by February 2024 GPT-4 Turbo (Jan 2024) leads with 75.2 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) 75.2
  2. 2 Qwen1.5-72B 71.6
  3. 3 文心一言4.0 70.7
  4. 4 GPT-4 Jun 2023 70.4
  5. 5 Qwen1.5-14B-Chat 69.3
  6. 6 讯飞星火V3.5 67.1
  7. 7 Yi-34B-Chat 66.5
  8. 8 GPT-3.5 Turbo Jan 2024 66.1
  9. 9 Baichuan2-13B-Chat 63.2
  10. 10 Chinese-Alpaca2-13B 61.5
  11. 11 ChatGLM3-6B 60.2
  12. 12 Llama-2-13B-Chat 55.9

Source: Official SuperCLUE-Role leaderboard

#EntryScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 75.2 Jan 2024 Official leaderboard
2 Qwen1.5-72B 71.6 Feb 2024 Official leaderboard
3 文心一言4.0 70.7 Official leaderboard
4 GPT-4 Jun 2023 70.4 Jun 2023 Official leaderboard
5 Qwen1.5-14B-Chat 69.3 Feb 2024 Official leaderboard
6 讯飞星火V3.5 67.1 Official leaderboard
7 Yi-34B-Chat 66.5 Official leaderboard
8 GPT-3.5 Turbo Jan 2024 66.1 Jan 2024 Official leaderboard
9 Baichuan2-13B-Chat 63.2 Sep 2023 Official leaderboard
10 Chinese-Alpaca2-13B 61.5 Official leaderboard
11 ChatGLM3-6B 60.2 Oct 2023 Official leaderboard
12 Llama-2-13B-Chat 55.9 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 75.2 Jan 2024 Official leaderboard
2 Qwen1.5-72B 71.6 Feb 2024 Official leaderboard
3 GPT-4 Jun 2023 70.4 Jun 2023 Official leaderboard
4 Qwen1.5-14B-Chat 69.3 Feb 2024 Official leaderboard
5 GPT-3.5 Turbo Jan 2024 66.1 Jan 2024 Official leaderboard
6 Baichuan2-13B-Chat 63.2 Sep 2023 Official leaderboard
7 ChatGLM3-6B 60.2 Oct 2023 Official leaderboard

Rankings by part

We read 16 parts from the benchmark’s own leaderboard in 3 groups: 角色基础, 角色风格 and 场景应用. Each ranks models on one part of the test. 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.

角色基础

7 models we track have a score here.

  1. 1 GPT-4 Turbo (Jan 2024) 78.4
  2. 2 GPT-4 Jun 2023 ↑1 73.5
  3. 3 Qwen1.5-72B ↓1 71.2
  4. 4 Qwen1.5-14B-Chat 62.0
  5. 5 GPT-3.5 Turbo Jan 2024 61.6
  6. 6 Baichuan2-13B-Chat 59.9
  7. 7 ChatGLM3-6B 55.7

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 Apr 2024

Source: Official SuperCLUE-Role 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
60.0 65.0 70.0 75.0 80.0 2023 2024 60.0 65.0 70.0 75.0 80.0 2023 2024

Source: Official SuperCLUE-Role 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 (12 entries).
  • Pass Models scored 7 models we track, plus 5 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 superclueai.com: 7 rows for models we track and 5 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