ZNO-Eval - archival release
Note: This dataset freezes the original ZNO-Eval task payloads (https://github.com/NLPForUA/ZNO) for reproducibility. It is not the recommended starting point for new evaluations: use ZNO-Eval v2, which repairs and annotates the major known problems without rewriting this archive.
The limitation is specifically that v1 does not reliably expose all source media, so those rows are often unavailable to a controlled text-only benchmark and may also be incomplete for multimodal use until reconstructed from the source.
Release in progress. Stay tuned.
Loading
from datasets import load_dataset
all_tasks = load_dataset("NLPForUA/zno-eval", split="all")
ukrainian = load_dataset("NLPForUA/zno-eval", split="ukrainian")
exams = load_dataset("NLPForUA/zno-eval", "exams", split="exams")
issues = load_dataset("NLPForUA/zno-eval", "issues", split="issues")
all is the deterministic concatenation of ukrainian, history, geography, and math. Subjects are dataset partitions, not train/validation/test splits.
Known limitations reviewed against v2
Counts below are affected task counts and overlap. Do not add them to estimate unique affected tasks. The complete row-level evidence is queryable through the issues configuration.
| Issue | Affected v1 tasks | Interpretation |
|---|---|---|
Source has media although with_photo=false |
105 | Unsafe for controlled text-only evaluation without a verified surrogate. |
| Answer-option media is not represented by legacy media fields | 193 | V1 can omit visual answer content. |
| Source has multiple media items | 231 | The single-primary-URL legacy shape is incomplete. |
| Blank answer text | 113 | Often media-bearing or incompletely parsed options. |
| Declared answer labels without answer records | 151 | Structural parser/data loss. |
| Noncanonical exact duplicates | 73 | Exclude for canonical sampling, retain for provenance. |
| Time-sensitive review candidates | 71 | Review historical answer context before prompting. |
| Confirmed time-sensitive tasks | 1 | Supply exam-time context or exclude. |
| Not machine gradable after review | 64 | Retain for provenance, not automatic scoring. |
| Not eligible for the reviewed canonical text-only protocol | 1,393 | This does not imply multimodal or alternative-protocol unavailability. |
The review found 660 v1 tasks with confirmed v2 corrections, represented by 746 task-level correction rows.
Task schema
Every row contains the original v1 task payload unchanged plus four identity/join fields.
| Field | Type | Meaning |
|---|---|---|
uid |
string | Stable task key subject:test_id:task_id. |
test_uid |
string | Foreign key to exams, subject:test_id. |
subject |
string | ukrainian, history, geography, or math. |
test_id |
string | Source test identifier. |
task_id |
integer | Original zero-based task position. |
question |
string | Legacy parsed question text. |
answers |
list of objects | Legacy option records containing answer and text. |
answer_vheader |
list or null | Legacy permitted response labels. |
answer_hheader |
list or null | Legacy matching/sequence slots. |
correct_answer |
list of strings | Legacy gold codes or literal values. |
comment |
string | Legacy source/parser comment. |
with_photo |
boolean | Legacy parser flag; not a complete media-availability signal. |
photo_url |
string or null | Legacy primary image URL when recorded. |
Raw (parsed) data format:
Question with one correct answer:
{
"task_id": 42,
"question": "Образ Прометея символізує силу й нескореність народу у творі Тараса Шевченка",
"answers": [
{
"answer": "А",
"text": "«Сон» («У всякого своя доля...»)"
},
{
"answer": "Б",
"text": "«Кавказ»"
},
{
"answer": "В",
"text": "«Гайдамаки»"
},
{
"answer": "Г",
"text": "«І мертвим, і живим...»"
},
{
"answer": "Д",
"text": "«Ісаія. Глава 35»"
}
],
"answer_vheader": [
"А",
"Б",
"В",
"Г",
"Д"
],
"answer_hheader": [],
"correct_answer": [
"Б"
],
"comment": "",
"with_photo": false
},
Question with multiple correct answers (each number from answer_hheader corresponds to letter from answer_vheader):
{
"task_id": 48,
"question": "Укажіть послідовність дій, необхідних для того, щоб зорієнтуватися на місцевості за Полярною зіркою.",
"answers": [
{
"answer": "А",
"text": "подумки з’єднати прямою лінією дві зірки, що знаходяться на краю «ковша»"
},
{
"answer": "Б",
"text": "продовжити уявну пряму лінію і відкласти на ній приблизно п’ять відрізків, рівних відстані між двома зірками на краю «ковша»"
},
{
"answer": "В",
"text": "визначити яскраву зірку в сузір’ї Малої Ведмедиці, яка вказує напрям на північ"
},
{
"answer": "Г",
"text": "знайти сузір’я Великої Ведмедиці (Великого Возу), яке нагадує ківш"
}
],
"answer_vheader": [
"А",
"Б",
"В",
"Г"
],
"answer_hheader": [
"1",
"2",
"3",
"4"
],
"correct_answer": [
"Г",
"А",
"Б",
"В"
],
"comment": "",
"with_photo": false
},
Sample prompting (NLPForUA/gemma-2-it-zno-cot-with-topic):
<bos><start_of_turn>user
Дайте розгорнуту відповідь на завдання, починаючи з ключового слова "Відповідь:" та використовуючи лише наведені нижче варіанти.
Завдання: З’ясуйте, якими частинами мови є виділені слова в реченні (цифра позначає наступне слово).
Сучасна людина, щоб бути (1)успішною, має вчитися (2)впродовж (3)усього життя, (4)опановуючи нові галузі знань.
Варіанти відповіді:
А – займенник
Б – прикметник
В – форма дієслова (дієприкметник)
Г – форма дієслова (дієприслівник)
Д – прийменник<end_of_turn>
<start_of_turn>model
Відповідь:
ТЕМА: Морфологія. Частини мови
Завдання перевіряє ваше вміння визначати частини мови.
Необхідно бути дуже уважним, тому що частиномовна приналежність конкретного слова часто залежить від контексту. Проаналізуймо кожне із запропонованих слів.
Слово успішною відповідає на питання яка? та вказує на ознаку предмета. Отже, це прикметник.
Слово впродовж не відповідає на питання, а лише поєднує слова в реченні. Отже, це прийменник.
Слово усього відповідає на питання що? і вказує на предмет, але не називає його. Отже, це займенник.
А от слово опановуючи відповідає на питання що роблячи? та вказує на додаткову дію підмета. Отже, це особлива форма дієслова дієприслівник.
Відповідь: 1–Б, 2–Д, 3–А, 4–Г.<end_of_turn>
Exams table
| Field | Type | Meaning |
|---|---|---|
test_uid |
string | Primary exam key. |
subject |
string | Exam subject. |
test_id |
string | Source test identifier. |
source_url |
string | Source exam page. |
num_tasks |
integer | Number of frozen v1 task rows in the exam. |
Issues table
Each row identifies one issue type for one task or catalog target.
| Field | Type | Meaning |
|---|---|---|
target_uid |
string | Affected task or exam/catalog key. |
scope |
string | task or exam_catalog. |
subject |
string | Subject join field. |
test_uid |
string | Exam join field. |
test_id |
string | Source test identifier. |
task_id |
integer or null | Task position; null for exam-level issues. |
issue_type |
string | Stable machine-readable issue class. |
status |
string | confirmed or review_candidate. |
severity |
string | Issue family such as data_error, text_only_limitation, or evaluation_risk. |
affected_field |
string | V1 field or logical content area involved. |
affected_count |
integer | Number of affected subitems represented by the row. |
evidence |
string | Concise classification reason. |
v2_action |
string | How v2 repairs, annotates, or filters the case. |
v2_correction_ids |
list of strings | Join keys into v2 changes when applicable. |
canonical_uid |
string or null | Canonical task for duplicate-related rows. |
details_json |
string | Canonical JSON for issue-specific details. |
License
Original ZNO and NMT examination statements, answer options, answer keys and examination media originate from publicly released Ukrainian standardized examinations. Copyright and related rights, where applicable, remain with the Ukrainian Center for Educational Quality Assessment, the relevant commissioned authors, and other identified rights holders. These materials are included for research, education, public-sector evaluation and reproducibility, with source attribution, relying on their official publication and applicable limitations and exceptions under Ukrainian law. NLPForUA does not grant rights it does not own. Commercial users should assess their intended use and obtain any additional permissions required from the relevant rights holders.
Citation
If you use ZNO-Eval, including either release, please cite the original benchmark paper:
@article{zno-eval-2024,
title = {ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian},
author = {Syromiatnikov, M. V. and Ruvinskaya, V. M. and Troynina, A. S.},
journal = {Informatics. Culture. Technology},
publisher = {Odesa Polytechnic National University},
number = {1},
pages = {186--191},
year = {2024},
month = sep,
doi = {10.15276/ict.01.2024.27},
url = {https://arxiv.org/abs/2501.06715}
}
- Downloads last month
- 14