The AI arena is free today

Open Superagent
AI OrganizationMaintains 1 benchmark

Lakera: AI benchmarks & research

AI security company. Maintains the B3 agent security benchmark.

Maintained by Lakera

1 benchmark

In one line

Lakera maintains B3 AI Security Benchmark (counts toward the LLM Stats Score, 1 model scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Lakera.

What is Lakera?

AI security company. Maintains the B3 agent security benchmark. On LLM Stats it maintains 1 benchmark, led by B3 AI Security Benchmark. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Lakera benchmarks count toward the LLM Stats Score?

B3 AI Security Benchmark counts toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Lakera's benchmarks?

Mistral Large 4 leads B3 AI Security Benchmark at 97.1% (1 model scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Lakera's official benchmark results?

Lakera's official site is https://www.lakera.ai. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.