CLEVA

HELM wrap of CLEVA, a 31-task Chinese LLM platform with standardized prompts, 370K test instances, and contamination-aware sampling.

Also known as: CLEVA: Chinese Language Models EVAluation Platform, Chinese Language Models EVAluation Platform

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorycomposite
Subcategory31-task Chinese LLM suite (applications, abilities, and harms) with standardized prompts
Page statusactive
Metrictask-dependent (exact match, Chinese ROUGE-2, Chinese BLEU, SacreBLEU, iBLEU, math exact match, and others)
Directionhigher_is_better
Dataset size370000
Dataset licenceCC BY-NC-ND 4.0
PublisherCUHK LaVi Lab; Shanghai AI Laboratory (collaboration); HELM integration by Stanford CRFM

What it measures

cleva is HELM's scenario family for CLEVA (Chinese Language Models EVAluation Platform), not one quiz. The model is tested in Chinese across application tasks (for example translation, summarization, dialogue, code synthesis) and ability tasks (subject knowledge, reasoning primitives, calculation, cultural knowledge, harms). CLEVA's claim is that Chinese evals were incomparable because prompts were not shared. HELM therefore downloads CLEVA's per-task JSONL plus prompt templates and inference parameters, then applies the chosen template. Language is Chinese except where a task is explicitly bilingual (en2zh / zh2en).

Task format

HELM run-spec function cleva with args task, optional subtask, prompt_id (0-based template index), and version (v1 in the paper and README). Adaptation is generation, joint multiple choice, or separate multiple choice according to each prompt file's meta.mul_as_gen flag. Data are served from http://39.108.215.175/data as per-task zip files.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub