general benchmark
Nexus
NexusRaven benchmark for evaluating function calling capabilities of large language models in zero-shot scenarios across cybersecurity tools and API interactions
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
Nexus leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 58.7% | 100.0% | 4 | C | |
| 2 | ME | 56.7% | 66.7% | 4 | C | |
| 3 | ME | 38.5% | 33.3% | 4 | C | |
| 4 | ME | 34.3% | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
Nexus highlights
The top published results on this benchmark's own scale.
What is Nexus?
Definition and scoring fields from the benchmark registry.
NexusRaven benchmark for evaluating function calling capabilities of large language models in zero-shot scenarios across cybersecurity tools and API interactions
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Nexus
- Modality
- text
- Primary category
- general
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- nexus|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Nexus.
Which model scores highest on Nexus?
Llama 3.1 405B Instruct is currently ranked first with 58.7%.
What does Nexus measure?
NexusRaven benchmark for evaluating function calling capabilities of large language models in zero-shot scenarios across cybersecurity tools and API interactions
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.