datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
code_generation
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
🏠 Home Page •
💻 GitHub Repository •
🏆 Leaderboard •
LiveCodeBench is a "live" updating benchmark for holistically evaluating code related capabilities of LLMs.
Particularly, it evaluates LLMs across a range of capabilties including code generation, self-repair, test output prediction, and code execution.
This is the code generation scenario of LiveCodeBench. It is also… See the full description on the dataset page: https://huggingface.co/datasets/livecodebench/code_generation.LiveCodeBench-CPP
LiveCodeBench-CPP: An Extension of LiveCodeBench for Contamination Free Evaluation in C++
Overview
LiveCodeBench-CPP includes 454 problems from the release_v6 of LiveCodeBench, covering the period from October 2024 to May 2025. These problems are sourced from AtCoder (287 problems) and LeetCode (167 problems).
AtCoder Problems: These require generated solutions to read inputs from standard input (stdin) and write outputs to standard output (stdout). For unit testing, the… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/LiveCodeBench-CPP.livecodebench
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Note: This is a clone of livecodebench/code_generation_lite updated to work with recent versions of the datasets library. The original repository uses a Python loading script which is no longer supported. This version provides the same data using the standard JSONL format for compatibility.
Dataset Description
LiveCodeBench is a "live" updating benchmark for holistically… See the full description on the dataset page: https://huggingface.co/datasets/bzantium/livecodebench.dataenvgym-livecodebench-solutionslivecodebench-plus
LiveCodeBench-v6-Plus
A curated coding benchmark of 91 problems selected by hardness/discrimination
(lcb-v6-plus). It combines two sources, all in one clean schema:
64 evolved problems — mutated/evolved variants from LiveCodeBench-v6
(each carries its seed_problem).
27 original problems — un-evolved AtCoder problems taken directly from
livecodebench/code_generation_lite
release v6 (seed_problem is null).
About BenchEvolver
The evolved problems were produced by… See the full description on the dataset page: https://huggingface.co/datasets/BenchEvolver/livecodebench-plus.ko-livecodebench
Ko-LiveCodeBench
This dataset is the livecodebench/code_generation_lite dataset with the question_content field translated to Korean.
Dataset Versions
The dataset provides multiple configurations (subsets) corresponding to different release versions:
release_v1: Problems released between May 2023 and Mar 2024 (400 problems)
release_v2: Problems released between May 2023 and May 2024 (511 problems)
release_v3: Problems released between May 2023 and Jul 2024 (612 problems)… See the full description on the dataset page: https://huggingface.co/datasets/bzantium/ko-livecodebench.LiveCodeBench-CodeGenerationlivecodebench-executeSynthia-S1-LiveCodeBench-Eval
Synthia S1 27B LiveCodeBench Outputs
Done generating outputs. Evaluating now...
LiveCodeBenchThis dataset stores preprocessed inputs for the original livecodebench/code_generation_lite dataset.
Dataset structure: task_name/llm_style/version_specific.json, in which:
task_name is the name of benchmark task, as LiveCodeBench consists of multiple tasks. Currently, we focus on the Code Generation task
llm_style identifies the LLM that the prompts are specialized for.
version_specific.json stores the samples. Since LiveCodeBench has different versions, we also stores different lists of… See the full description on the dataset page: https://huggingface.co/datasets/LoneResearch/LiveCodeBench.TDAR_Eval-LiveCodeBenchlivecodebench-th