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 13 thg 2, 2024+ more versions - h
malicious-llm-prompts
- huggingface.co
- h
llm-prompt-collection
- huggingface.co
Updated 28 thg 4, 2026 - h
llm-prompt-injection-attacks
- huggingface.co
+ more versions - h
drh-System-Prompt-processed
- huggingface.co
Updated 23 thg 5, 2025 - h
malicious-llm-prompts-v3
- huggingface.co
+ more versions - h
Long-Prompt-Experiment
- huggingface.co
Updated 13 thg 9, 2025 - h
system-prompt-leakage
- huggingface.co
- h
ParallelPrompt
- huggingface.co
Updated 23 thg 6, 2025 - h
system-prompt-dataset
- huggingface.co
- h
llm-redteam-corpus-taxonomy-core
- huggingface.co
prompt-injections
- huggingface.co
Updated 17 thg 5, 2023- h
turkish-llm-injection
- huggingface.co
- h
llm-prompt-recovery
- huggingface.co
- h
in-the-wild-jailbreak-prompts
- huggingface.co
+ more versions - h
llm-cost-same-prompt
- huggingface.co
Updated 6 thg 8, 2026 - h
multi-turn-conversations
- huggingface.co
- h
llm-refusal-evaluation
- huggingface.co
- h
llm-attacked-prompts-clm
- huggingface.co
- h
llm-security-en
- huggingface.co
Updated 13 thg 2, 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
13 thg 2, 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.