ViLLM-Eval
Models answer Vietnamese exam, general knowledge, and reading comprehension questions. They also predict the final word in a passage.
The harness reports accuracy and also reports perplexity for word prediction. The organizers released individual tasks in 2023 and the named harness in April 2024.
- Made by
- Ton Duc Thang University, INT2 and HPC SYSTEMS
- Released
- April 2024
- Kind
- Knowledge in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- Vietnamese
- Interaction
- Single turn
- Items from
- Exams and contests, Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
greennode-14b tops the leaderboard with 40.3%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The board reports no combined score, so the headline is normalized accuracy on ARC-vi, its first public task. 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.
- 1 greennode-14b 40.3%
- 2 cpt-smartbot-13b 39.7%
- 3 ura-llama-13b 37.5%
- 4 vietcuna-7b-v3 33.5%
- 5 greennode-7b 31.6%
- 6 hoa-7b 28.6%
- 7 hoa-1b4 27.2%
- 8 gpt-j-6B-vietnamese-news 24.2%
- 9 gpt-neo-1.3B-vietnamese-news 22.7%
Source: Official ViLLM-Eval leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | greennode-14b | 40.3% | GreenNode.ai | Official leaderboard | ||
| 2 | cpt-smartbot-13b | 39.7% | CPT_Smartbot | Official leaderboard | ||
| 3 | ura-llama-13b | 37.5% | ura-hcmut | Official leaderboard | ||
| 4 | vietcuna-7b-v3 | 33.5% | vilm | Official leaderboard | ||
| 5 | greennode-7b | 31.6% | GreenNode.ai | Official leaderboard | ||
| 6 | hoa-7b | 28.6% | vlsp-2023-vllm | Official leaderboard | ||
| 7 | hoa-1b4 | 27.2% | vlsp-2023-vllm | Official leaderboard | ||
| 8 | gpt-j-6B-vietnamese-news | 24.2% | VietAI | Official leaderboard | ||
| 9 | gpt-neo-1.3B-vietnamese-news | 22.7% | VietAI | Official 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 Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 9 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 9 entries at the last read, none a model we track.
- 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.