Nexus Function Calling - VT Multi Disconnected: leaderboard

The "VT Multi Disconnected" subtask of Nexus Function Calling. Nexus Function Calling: Evaluates tool calling, API use, function selection, structured arguments, and multi-step tool workflows.

Metric: Function Call Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 4 models tracked.

Top models

#ModelScoreOverall rank
1NexusRaven-V2-13B42.86#1382
2GPT-4 Preview (1106)28.57#418
3GPT-3.5 Turbo (1106)14.29#961

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=nexus-function-calling-vt-multi-disconnected · How It Works · Data refreshed daily, snapshot 2026-10-20.