Lakera with the UK AI Security Institute
b3: Backbone Breaker Benchmark
Lakera's open-source benchmark of how well the LLM inside an AI agent resists attacks such as system-prompt exfiltration, malicious code injection and tool-call manipulation. Higher means more attacks resisted.
ModelsModels with a result.4
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.2025
Results
4 results#ModelResultThe score from the source.
