Nexus Function Calling

Nexus Function Calling: Evaluates tool calling, API use, function selection, structured arguments, and multi-step tool workflows.

4rows
scoreprimary metric
2026-05-06sampled

Metadata

Metrics

All Tasks Average, Tasks with Single Call Average, Nested/Parallel Calls Average, Climate, Heldout Combined, Places API, OTX, VirusTotal, VT Multi Dependency, VT Multi Disconnected, CVECPE, CVECPE Multi Dependency

Latest Results

Rank Subject All Tasks Average Model Match Provenance Sampled
1 NexusRaven-V2 58.20 Imported 2026-05-06
2 GPT4-1106 54.18 GPT-4
openai-gpt-4
Imported 2026-05-06
3 GPT3.5 37.45 Imported 2026-05-06
4 Gorilla open-function-v1 6.23 Imported 2026-05-06