OMNIX Benchmarks 是一个用于评估和基准测试大型语言模型性能的数据集。它旨在通过一套标准化的指标对模型进行综合比较，涵盖格式遵循、逻辑推理、知识回忆、约束遵循、成功率（首次通过和最终）以及推理延迟等多个关键维度。该数据集支持文本生成和问答任务类别，并提供了对多个流行模型（如 Qwen、Gemma、Llama 等系列的不同版本）在上述维度上的量化评分和排名分析，帮助研究人员和开发者了解

Hugging Face2026-07-07 更新100

smalleval/mmlu-nano

大型语言模型评估

多任务语言理解

# SmallEval: Browser-Friendly LLM Evaluation Datasets 🚀 [![Created by Cloud Code AI](https://img.shields.io/badge/Created%20by-Cloud%20Code%20AI-blue)](https://cloudcode.ai) SmallEval is a curated

Hugging Face2025-01-20 更新90

DCAgent2/dev_set_v2_100k_epochs3__Qwen3_8B_20260325_231128

大型语言模型评估

指令微调

--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: agent dtype: string - name: model dtype

Hugging Face2026-03-26 更新110

Validation queries for the paper OKG-Soft: An Open Knowledge Graph with Machine Readable Scientific Software Metadata

知识图谱

科学软件

Validation queries for the paper OKG-Soft: An Open Knowledge Graph with Machine Readable Scientific Software Metadata. The queries are shown in SPARQL along with the results obtained when they were e

NIAID Data Ecosystem90

GPT-4 automated tests and evaluation

资源简介：

相关数据集