Horizon-Labs/content-safety-leaderboard

Space

A same-script comparison of open content-safety / moderation classifiers (prompt and response harm, toxicity, over-blocking).

2 commits

1 linked in READMEs

updated Sep 27, 2026

See the code

README

A same-script comparison of open content-safety / moderation classifiers (prompt and response harm, toxicity, over-blocking). See the page for the method and caveats.

static

Similar repos

Horizon-Labs/prompt-injection-leaderboard

Space

A same-script comparison of open prompt-injection / jailbreak classifiers. See the page for the…

Horizon-Labs/content-safety-guard-base

Model

Content Safety Guard (base, 308M)

Horizon-Labs/content-safety-guard

Space

Runs Horizon-Labs/content-safety-guard-small (int8-embedding

Horizon-Labs/multilingual-zeroshot-leaderboard

Space

A same-script comparison of open NLI-based zero-shot classifiers (transformers…

6rightjade/expguardmix

Dataset

musubilabs/policylm-1.7b

Model

PolicyLM-1.7B

Freshma/HarmProfile

Dataset

leaf-pear/Lingua-SafetyBench

Dataset

Linked in READMEs

horizon-ai-labs/agent-io-guards

Code for small open models that guard LLM apps: prompt-injection detection, PII redaction,…

README badge

Horizon-Labs/content-safety-leaderboard

Space

A same-script comparison of open content-safety / moderation classifiers (prompt and response harm, toxicity, over-blocking).

2 commits

1 linked in READMEs

updated Sep 27, 2026

See the code

README

A same-script comparison of open content-safety / moderation classifiers (prompt and response harm, toxicity, over-blocking). See the page for the method and caveats.

static