Accessibility: Skip TopNav
Tool-Calling Model Comparison
Comparisons of tool-calling benchmarks (Tau2-Bench, Terminal Bench Hard, and BFCL v4) for GPT-OSS 20B, GPT-OSS 120B, HyperNova 60B 2512, and HyperNova 60B 2602.
Format
PNG
Source
Multiverse Computing
Downloads
Original
Large
Medium
Small