Taiwanese Mandarin Language Understanding
Models answer questions from Taiwanese exams in traditional Chinese. The subjects range from school topics to professional qualifications.
- Made by
- Po-Heng Chen and colleagues
- Released
- March 2024
- Kind
- Knowledge in many languages
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- Chinese
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-4 Turbo Apr 2024 #172 on the capability index
- Last model added
- April 2024
- Scores refreshed
- November 20th, 2026
Claude 3 Opus leads with 73.6% among models released by April 2024 Claude 3 Opus leads with 73.6% among models released by April 2024
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 April 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
- 73.6 Claude 3 Opus
- 70.4 GPT-4 Turbo
- 68.5 Yi-34B-Chat
- 61.8
Qwen-14B
- 61.4
Gemini 1.0 Pro
- 54.8 Qwen-7B-Chat
- 54.4 Claude Instant
- 51.3 Breeze-7B-Instruct
- 49.4 GPT-3.5 π
- 46.4 Mixtral-8x7B-Instruct
- 46.4 ChatGLM3-6B
- 44.6 Claude 2
- 44.3
Mistral-7B-Instruct-v0.1
- 42.9 Taiwan-LLM-13B-Chat
- 41.2 Baichuan2-13B-Chat
- 37.4 Taiwan-LLM-7B-Chat
- 35.5 falcon-40b-instruct
- 34.6
OLMo-7B-Instruct
- 34.4 Llama-2-13b-Chat
- 32.8
Yi-6B-Chat
- 31.6 Qwen-0.5B-Chat
- 28.0 Llama-2-7b-chat
- 25.7 Falcon-7b-instruct
- 25.6 Gemma-7b-it
- 1 Claude 3 Opus 73.6%
- 2 GPT-4 Turbo Apr 2024 70.4%
- 3 Yi-34B-Chat 68.5%
- 4
Qwen-14B 61.8%
- 5
Gemini 1.0 Pro 61.4%
- 6 Qwen-7B-Chat 54.8%
- 7 Claude Instant 54.4%
- 8 Breeze-7B-Instruct 51.3%
- 9 GPT-3.5 π 49.4%
- 10 Mixtral-8x7B-Instruct 46.4%
- 11 ChatGLM3-6B 46.4%
- 12 Claude 2 44.6%
- 13
Mistral-7B-Instruct-v0.1 44.3%
- 14 Taiwan-LLM-13B-Chat 42.9%
- 15 Baichuan2-13B-Chat 41.2%
- 16 Taiwan-LLM-7B-Chat 37.4%
- 17 falcon-40b-instruct 35.5%
- 18
OLMo-7B-Instruct 34.6%
- 19 Llama-2-13b-Chat 34.4%
- 20
Yi-6B-Chat 32.8%
- 21 Qwen-0.5B-Chat 31.6%
- 22 Llama-2-7b-chat 28%
- 23 Falcon-7b-instruct 25.7%
- 24 Gemma-7b-it 25.6%
Source: The Taiwanese Mandarin Language Understanding paper
- 1 Claude 3 Opus 73.6%
- 2 GPT-4 Turbo Apr 2024 70.4%
- 3
Qwen-14B 61.8%
- 4
Gemini 1.0 Pro 61.4%
- 5 Claude Instant 54.4%
- 6 ChatGLM3-6B 46.4%
- 7 Claude 2 44.6%
- 8
Mistral-7B-Instruct-v0.1 44.3%
- 9 Baichuan2-13B-Chat 41.2%
- 10
OLMo-7B-Instruct 34.6%
- 11
Yi-6B-Chat 32.8%
Source: The Taiwanese Mandarin Language Understanding paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude 3 Opus | 73.6% | Feb 2024 | Official leaderboard | |
| 2 | GPT-4 Turbo Apr 2024 | 70.4% | Apr 2024 | Official leaderboard | |
| 3 | Yi-34B-Chat | 68.5% | Official leaderboard | ||
| 4 | | 61.8% | Sep 2023 | Official leaderboard | |
| 5 | | 61.4% | Dec 2023 | Official leaderboard | |
| 6 | Qwen-7B-Chat | 54.8% | Official leaderboard | ||
| 7 | Claude Instant | 54.4% | Aug 2023 | Official leaderboard | |
| 8 | Breeze-7B-Instruct | 51.3% | Official leaderboard | ||
| 9 | GPT-3.5 π | 49.4% | Official leaderboard | ||
| 10 | Mixtral-8x7B-Instruct | 46.4% | Official leaderboard | ||
| 11 | ChatGLM3-6B | 46.4% | Oct 2023 | Official leaderboard | |
| 12 | Claude 2 | 44.6% | Jul 2023 | Official leaderboard | |
| 13 | | 44.3% | Sep 2023 | Official leaderboard | |
| 14 | Taiwan-LLM-13B-Chat | 42.9% | Official leaderboard | ||
| 15 | Baichuan2-13B-Chat | 41.2% | Sep 2023 | Official leaderboard | |
| 16 | Taiwan-LLM-7B-Chat | 37.4% | Official leaderboard | ||
| 17 | falcon-40b-instruct | 35.5% | Official leaderboard | ||
| 18 | | 34.6% | Feb 2024 | Official leaderboard | |
| 19 | Llama-2-13b-Chat | 34.4% | Official leaderboard | ||
| 20 | | 32.8% | Nov 2023 | Official leaderboard | |
| 21 | Qwen-0.5B-Chat | 31.6% | Official leaderboard | ||
| 22 | Llama-2-7b-chat | 28% | Official leaderboard | ||
| 23 | Falcon-7b-instruct | 25.7% | Official leaderboard | ||
| 24 | Gemma-7b-it | 25.6% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude 3 Opus | 73.6% | Feb 2024 | Official leaderboard | |
| 2 | GPT-4 Turbo Apr 2024 | 70.4% | Apr 2024 | Official leaderboard | |
| 3 | | 61.8% | Sep 2023 | Official leaderboard | |
| 4 | | 61.4% | Dec 2023 | Official leaderboard | |
| 5 | Claude Instant | 54.4% | Aug 2023 | Official leaderboard | |
| 6 | ChatGLM3-6B | 46.4% | Oct 2023 | Official leaderboard | |
| 7 | Claude 2 | 44.6% | Jul 2023 | Official leaderboard | |
| 8 | | 44.3% | Sep 2023 | Official leaderboard | |
| 9 | Baichuan2-13B-Chat | 41.2% | Sep 2023 | Official leaderboard | |
| 10 | | 34.6% | Feb 2024 | Official leaderboard | |
| 11 | | 32.8% | Nov 2023 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Taiwanese Mandarin Language Understanding paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Taiwanese Mandarin Language Understanding 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in April 2024, for GPT-4 Turbo. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (24 entries).
- Pass Models scored 11 models we track, plus 13 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in April 2024, for GPT-4 Turbo.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 Turbo (#172).
- Pass Headroom The best is 73.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 rows for models we track and 13 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.