SuperCLUE-Role
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
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4 Turbo (Jan 2024) 75.2
- 2
Qwen1.5-72B 71.6
- 3 文心一言4.0 70.7
- 4 GPT-4 Jun 2023 70.4
- 5
Qwen1.5-14B-Chat 69.3
- 6 讯飞星火V3.5 67.1
- 7 Yi-34B-Chat 66.5
- 8 GPT-3.5 Turbo Jan 2024 66.1
- 9 Baichuan2-13B-Chat 63.2
- 10 Chinese-Alpaca2-13B 61.5
- 11 ChatGLM3-6B 60.2
- 12 Llama-2-13B-Chat 55.9
Source: Official SuperCLUE-Role leaderboard
- 1 GPT-4 Turbo (Jan 2024) 75.2
- 2
Qwen1.5-72B 71.6
- 3 GPT-4 Jun 2023 70.4
- 4
Qwen1.5-14B-Chat 69.3
- 5 GPT-3.5 Turbo Jan 2024 66.1
- 6 Baichuan2-13B-Chat 63.2
- 7 ChatGLM3-6B 60.2
Source: Official SuperCLUE-Role leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo (Jan 2024) | 75.2 | Jan 2024 | Official leaderboard | |
| 2 | | 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 | | 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 |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo (Jan 2024) | 75.2 | Jan 2024 | Official leaderboard | |
| 2 | | 71.6 | Feb 2024 | Official leaderboard | |
| 3 | GPT-4 Jun 2023 | 70.4 | Jun 2023 | Official leaderboard | |
| 4 | | 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 GPT-4 Turbo (Jan 2024) 78.4
- 2 GPT-4 Jun 2023 ↑1 73.5
- 3
Qwen1.5-72B ↓1 71.2
- 4
Qwen1.5-14B-Chat 62.0
- 5 GPT-3.5 Turbo Jan 2024 61.6
- 6 Baichuan2-13B-Chat 59.9
- 7 ChatGLM3-6B 55.7
角色风格
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 75.4
- 2
Qwen1.5-14B-Chat ↑2 72.7
- 3
Qwen1.5-72B ↓1 72.5
- 4 GPT-4 Jun 2023 ↓1 70.6
- 5 GPT-3.5 Turbo Jan 2024 67.9
- 6 Baichuan2-13B-Chat 62.9
- 7 ChatGLM3-6B 61.3
场景应用
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 74.0
- 2
Qwen1.5-72B 71.3
- 3
Qwen1.5-14B-Chat ↑1 69.9
- 4 GPT-4 Jun 2023 ↓1 69.2
- 5 GPT-3.5 Turbo Jan 2024 66.7
- 6 Baichuan2-13B-Chat 64.5
- 7 ChatGLM3-6B 61.2
基础总分
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 78.4
- 2 GPT-4 Jun 2023 ↑1 73.5
- 3
Qwen1.5-72B ↓1 71.2
- 4
Qwen1.5-14B-Chat 62.0
- 5 GPT-3.5 Turbo Jan 2024 61.6
- 6 Baichuan2-13B-Chat 59.9
- 7 ChatGLM3-6B 55.7
知识掌握
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 76.6
- 2 GPT-4 Jun 2023 ↑1 72.2
- 3
Qwen1.5-72B ↓1 65.8
- 4 GPT-3.5 Turbo Jan 2024 ↑1 49.8
- 5
Qwen1.5-14B-Chat ↓1 48.4
- 6 Baichuan2-13B-Chat 47.0
- 7 ChatGLM3-6B 41.6
对话能力
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 80.2
- 2
Qwen1.5-72B 76.6
- 3
Qwen1.5-14B-Chat ↑1 75.6
- 4 GPT-4 Jun 2023 ↓1 74.8
- 5 GPT-3.5 Turbo Jan 2024 73.4
- 6 Baichuan2-13B-Chat 72.8
- 7 ChatGLM3-6B 69.8
风格总分
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 75.4
- 2
Qwen1.5-14B-Chat ↑2 72.7
- 3
Qwen1.5-72B ↓1 72.5
- 4 GPT-4 Jun 2023 ↓1 70.6
- 5 GPT-3.5 Turbo Jan 2024 67.9
- 6 Baichuan2-13B-Chat 62.9
- 7 ChatGLM3-6B 61.3
语言风格
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 72.6
- 2
Qwen1.5-72B 72.4
- 3
Qwen1.5-14B-Chat ↑1 71.8
- 4 GPT-4 Jun 2023 ↓1 70.8
- 5 GPT-3.5 Turbo Jan 2024 66.8
- 6 Baichuan2-13B-Chat 61.6
- 7 ChatGLM3-6B 58.4
行为习惯
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 77.6
- 2
Qwen1.5-14B-Chat ↑2 72.6
- 3
Qwen1.5-72B ↓1 72.2
- 4 GPT-4 Jun 2023 ↓1 71.6
- 5 GPT-3.5 Turbo Jan 2024 68.4
- 6 Baichuan2-13B-Chat 62.8
- 7 ChatGLM3-6B 61.6
角色背景
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 76.0
- 2
Qwen1.5-14B-Chat ↑2 73.6
- 3
Qwen1.5-72B ↓1 73.0
- 4 GPT-4 Jun 2023 ↓1 69.4
- 5 GPT-3.5 Turbo Jan 2024 68.4
- 6 Baichuan2-13B-Chat 64.4
- 7 ChatGLM3-6B 64.0
应用总分
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 74.0
- 2
Qwen1.5-72B 71.3
- 3
Qwen1.5-14B-Chat ↑1 69.9
- 4 GPT-4 Jun 2023 ↓1 69.2
- 5 GPT-3.5 Turbo Jan 2024 66.7
- 6 Baichuan2-13B-Chat 64.5
- 7 ChatGLM3-6B 61.2
情感陪伴
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 79.2
- 2
Qwen1.5-72B 77.0
- 3
Qwen1.5-14B-Chat ↑1 73.8
- 4 GPT-4 Jun 2023 ↓1 72.6
- 5 GPT-3.5 Turbo Jan 2024 71.2
- 6 ChatGLM3-6B ↑1 67.4
- 7 Baichuan2-13B-Chat ↓1 67.2
游戏NPC
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 77.2
- 2 GPT-4 Jun 2023 ↑1 74.0
- 3
Qwen1.5-72B ↓1 72.6
- 4 GPT-3.5 Turbo Jan 2024 ↑1 68.6
- 5
Qwen1.5-14B-Chat ↓1 68.4
- 6 Baichuan2-13B-Chat 64.0
- 7 ChatGLM3-6B 59.4
社交场景
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 76.4
- 2
Qwen1.5-14B-Chat ↑2 74.0
- 3
Qwen1.5-72B ↓1 72.6
- 4 Baichuan2-13B-Chat ↑2 70.4
- 5 GPT-4 Jun 2023 ↓2 70.2
- 6 GPT-3.5 Turbo Jan 2024 ↓1 69.0
- 7 ChatGLM3-6B 63.6
直播营销
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 70.2
- 2
Qwen1.5-72B 69.6
- 3
Qwen1.5-14B-Chat ↑1 68.0
- 4 GPT-4 Jun 2023 ↓1 65.0
- 5 GPT-3.5 Turbo Jan 2024 63.8
- 6 Baichuan2-13B-Chat 63.4
- 7 ChatGLM3-6B 61.2
影音名人
7 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) 67.2
- 2
Qwen1.5-14B-Chat ↑2 65.2
- 3
Qwen1.5-72B ↓1 64.8
- 4 GPT-4 Jun 2023 ↓1 64.0
- 5 GPT-3.5 Turbo Jan 2024 60.8
- 6 Baichuan2-13B-Chat 57.6
- 7 ChatGLM3-6B 54.2
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
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.
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
- 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.