datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
AICoderEvalspm-synthetic-questions
Dataset Card: SPM Synthetic Questions
Dataset Summary
14,135 synthetic exam-style questions for Malaysia's SPM (Sijil Pelajaran
Malaysia) curriculum, Form 5, covering 10 subjects. Every item is
LLM-generated and aligned to the KSSM curriculum and the SPM examination
format. Each item belongs to one of three categories:
hots — Higher Order Thinking Skills (KBAT) questions
lazim — soalan lazim (commonly-asked question styles)
perangkap — soalan perangkap (trap… See the full description on the dataset page: https://huggingface.co/datasets/VixeroAI/spm-synthetic-questions.MalayMMLU-Eval
VixeroAI — MalayMMLU Evaluation
Benchmark package for evaluating base Qwen 3.8‑27B on the MalayMMLU Malay-language multiple-choice benchmark (24,213 items, 5 categories / 22 subjects).
Headline result — zero-shot recovered accuracy 83.35% (strict first-token 82.67%).
The purpose of this repo is reproducibility and defensibility: every number in the report is derivable from the committed raw results and the committed (dependency-free) harness.
Results
Metric… See the full description on the dataset page: https://huggingface.co/datasets/VixeroAI/MalayMMLU-Eval.vi_xlinghealthvixen