ZhoBLiMP
Models compare pairs of Chinese sentences that differ in grammatical acceptability. Accuracy measures how often the model prefers the grammatical sentence.
- Made by
- Yikang Liu and colleagues
- Released
- November 2024
- Kind
- Reading in many languages
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Chinese
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
Zh-Pythia-1.4B tops the leaderboard with 90% Qwen2.5-14B leads with 87.2%
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. The best model we track is Qwen2.5-14B, at 87.2%. This view shows only models we track, each at its best.
- 1 Zh-Pythia-1.4B SLLN-LP 90%
- 2 Zh-Pythia-410M SLLN-LP 89.1%
- 3
Qwen2.5-14B SLLN-LP 87.2%
- 4 Zh-Pythia-160M SLLN-LP 87%
- 5
Qwen2.5-7B SLLN-LP 86.7%
- 6 Zh-Pythia-70M SLLN-LP 83.9%
- 7 Zh-Pythia-14M SLLN-LP 79.1%
Source: The ZhoBLiMP paper
- 1
Qwen2.5-14B SLLN-LP 87.2%
- 2
Qwen2.5-7B SLLN-LP 86.7%
Source: The ZhoBLiMP paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Zh-Pythia-1.4B | 90% | SLLN-LP | Official leaderboard | |
| 2 | Zh-Pythia-410M | 89.1% | SLLN-LP | Official leaderboard | |
| 3 | | 87.2% | SLLN-LP | Sep 2024 | Official leaderboard |
| 4 | Zh-Pythia-160M | 87% | SLLN-LP | Official leaderboard | |
| 5 | | 86.7% | SLLN-LP | Sep 2024 | Official leaderboard |
| 6 | Zh-Pythia-70M | 83.9% | SLLN-LP | Official leaderboard | |
| 7 | Zh-Pythia-14M | 79.1% | SLLN-LP | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 87.2% | SLLN-LP | Sep 2024 | Official leaderboard |
| 2 | | 86.7% | SLLN-LP | Sep 2024 | 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 ZhoBLiMP paper
Qwen2.5-14B on the official leaderboard passed 85% in September 2024
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ZhoBLiMP 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (7 entries).
- Pass Models scored 2 models we track, plus 5 other entries on its leaderboard.
- Note Newest score The newest came 2 years ago, in September 2024, for Qwen2.5-14B. That’s expected for a saturated test.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Saturated. The best is 87.2%, past 85% since September 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 6 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.