Saved datasets
arrow_drop_downLast updated
arrow_drop_downDownload format
Croissant
Croissant is a format for Machine Learning datasets
Learn more about this at mlcommons.org/croissant.
arrow_drop_downUsage rights
License from data provider
Please review the applicable license to make sure your contemplated use is permitted.
arrow_drop_downTopic
arrow_drop_downProvider
Free
Cost to access
Described as free to access or have a license that allows redistribution.
100+ datasets found
- h
llm-system-prompts-benchmark
- huggingface.co
Updated Feb 13, 2024 - h
synthetic_multilingual_llm_prompts
- huggingface.co
Updated Jun 11, 2024 - h
awesome-chatgpt-prompts
- huggingface.co
Updated Dec 15, 2023+ more versions - h
malicious-llm-prompts-v4
- huggingface.co
Updated Jan 26, 2025+ more versions - h
llm-evaluation-prompts
- huggingface.co
Updated Dec 24, 2025 - h
prompt-injections
- huggingface.co
Updated May 4, 2025+ more versions - h
Official_LLM_System_Prompts
- huggingface.co
Updated Dec 27, 2025 - h
speedrender-llm-prompt
- huggingface.co
Updated Feb 12, 2025 - h
in-the-wild-jailbreak-prompts
- huggingface.co
Updated Aug 7, 2023 - h
LLM_Bash
- huggingface.co
Updated Mar 1, 2023 llmail-inject-challenge
- huggingface.co
Updated May 14, 2025real-toxicity-prompts
- huggingface.co
Updated Sep 24, 2020+ more versions- h
drh-System-Prompt-Library
- huggingface.co
Updated Aug 7, 2025 - h
malicious-llm-prompts
- huggingface.co
Updated Mar 9, 2009 - h
harmful-dataset
- huggingface.co
Updated Jul 24, 2024 - h
llm-prompt-injection-attacks
- huggingface.co
Updated Jan 24, 2026 - h
OpenEndedLLMPrompts
- huggingface.co
Updated Dec 31, 2023 - h
llm-prompt-recovery
- huggingface.co
- h
deepseek-r1-reasoning-prompts
- huggingface.co
Updated Aug 10, 2024 - h
llm-aes-writing-prompts-deduplicated-0.9-similarity
- huggingface.co
Updated Jan 13, 2026
Share
Facebook
Twitter
EmailClick to copy link
Link copied
Cite
Naomi Bashkansky (2024). llm-system-prompts-benchmark [Dataset]. https://huggingface.co/datasets/Naomibas/llm-system-prompts-benchmark
llm-system-prompts-benchmark
Naomibas/llm-system-prompts-benchmark
100 system prompts for benchmarking large language models
CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
Dataset updated
Feb 13, 2024Authors
Naomi Bashkansky License
Apache License, v2.0https://www.apache.org/licenses/LICENSE-2.0
License information was derived automatically
Description
Dataset Card for Dataset Name
This datset is a collection of 100 system prompts for large language models.
Dataset Details
Dataset Description
These 100 system prompts test a model's ability to follow grammatical patterns; answer basic multiple choice questions; act according to a particular persona; memorize information; and speak in French. Files:
hundred_system_prompts.py: refer to this to see the (prompt, probe, function) triplets, as well as the… See the full description on the dataset page: https://huggingface.co/datasets/Naomibas/llm-system-prompts-benchmark.