refusal-benchmark

What is refusal-benchmark?

Measures LLM refusal rates on a set of harmful prompts via OpenAI-compatible endpoints. Benchmark Radar tracks refusal-benchmark, cited by 1 source documents…

Released

2026-08-22

Evaluates

Finance, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://github.com/audn-ai/refusal-benchmark

refusal-benchmark code

• Code https://github.com/audn-ai/refusal-benchmark
• Website https://audn.ai/audncode

Which sources cite refusal-benchmark?

• refusal-benchmark

Related Finance, Language & Knowledge, cs.AI benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench
• AdvancedMathBench
• AdversaBench