Nexus

Name: Nexus Leaderboard — AI Model Scores
Creator: LLM Stats
License: https://llm-stats.com/legal/terms-of-service

Paper

Progress Over Time

Interactive timeline showing model performance evolution on Nexus

State-of-the-art frontier

Open

Proprietary

Nexus Leaderboard

4 models

			Context	Cost
1	Llama 3.1 405B Instruct Meta	405B	—	—
2	Llama 3.1 70B Instruct Meta	70B	—	—
3	Llama 3.1 8B Instruct Meta	8B	—	—
4	Llama 3.2 3B Instruct Meta	3B	—	—

Notice missing or incorrect data?

About this benchmark

What is Nexus?

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

Nexus is a text benchmark evaluating models on general and tool calling tasks. LLM Stats tracks 4 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.

Compare leaders on the best AI for general and best AI for tool calling leaderboards.

Current leaders

Llama 3.1 405B Instruct from Meta currently leads the Nexus leaderboard with a score of 0.587 across 4 evaluated AI models.

Llama 3.1 405B InstructMeta58.7%

Llama 3.1 70B InstructMeta56.7%

Llama 3.1 8B InstructMeta38.5%

FAQ

Common questions about the Nexus benchmark and leaderboard.

What is the Nexus benchmark?

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

What is the Nexus leaderboard?

The Nexus leaderboard ranks 4 AI models based on their performance on this benchmark. Currently, Llama 3.1 405B Instruct by Meta leads with a score of 0.587. The average score across all models is 0.470.

What is the highest Nexus score?

The highest Nexus score is 0.587, achieved by Llama 3.1 405B Instruct from Meta.

How many models are evaluated on Nexus?

4 models have been evaluated on the Nexus benchmark, with 0 verified results and 4 self-reported results.

Where can I find the Nexus paper?

The Nexus paper is available at https://openreview.net/pdf?id=5lcPe6DqfI. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does Nexus cover?

Nexus is categorized under general and tool calling. The benchmark evaluates text models.

What is the best open-source model on Nexus?

Llama 3.1 405B Instruct by Meta is the top-ranked open-source model on Nexus, with a score of 0.587 (rank #1).

How recent are the Nexus leaderboard results?

The Nexus leaderboard was last updated in August 2026 and currently includes 4 evaluated models.