Wikibench

Nexus

general

NexusRaven benchmark for evaluating function calling capabilities of large language models in zero-shot scenarios across cybersecurity tools and API interactions

Leaderboard

Showing 4 of 4 results

  1. Llama 3.1 405B Instruct
    58.7%
    i
  2. Llama 3.1 70B Instruct
    56.7%
    i
  3. Llama 3.1 8B Instruct
    38.5%
    i
  4. Llama 3.2 3B Instruct
    34.3%
    i