unsafe-eval leaderboard
Tests how well AI safety filters catch harmful content. Researchers only.
CategoryFor Developers
SourceHugging Face Spaces
Traction10 likes
First seenOct 1, 2026
Quick facts
- What it is: unsafe-eval leaderboard is a for developers tool. Tests how well AI safety filters catch harmful content. Researchers only.
- Where it was found: Hugging Face Spaces, first seen Oct 1, 2026, with 10 traction when last checked.
- Tags: Benchmark, Hugging Face Space.
- Official link: huggingface.co/spaces/principled-intelligence/unsafe-eval-leaderboard
Featured in
Related tools
🧠 For Developers631 likes
Jev Decision Index
Scores and news about copies of Jev, an AI decision model. Researchers only.
TechnicalBenchmark · Hugging Face Space
🧠 For Developers14146 likes
Open LLM Leaderboard
A scoreboard that compares free AI models. Mostly useful to tech people.
TechnicalBenchmark · Hugging Face Space
🧠 For Developers7729 likes
MTEB Leaderboard
A scoreboard that compares AI search models. For programmers.
TechnicalRAG · Embeddings
🧠 For Developers2127 likes
UGI Leaderboard
Ranks AI models by how freely they answer touchy questions. Researchers only.
TechnicalBenchmark · Hugging Face Space
🧠 For Developers70 likes
S1MB Leaderboard
Scores comparing small decision-making AI models on 100+ tests. Researchers only.
TechnicalBenchmark · Hugging Face Space
🧠 For Developers135 likes
Open SLM Leaderboard
A scoreboard comparing small AI models. Developers only.
TechnicalBenchmark · Hugging Face Space
Is this your tool? Claim & feature it.