List your company
ResearchFormerly WizWand

Function Calling on BFCL (Accuracy %)

86.67Accuracy (%)Opus-4.6 (1M)
-3.466819.934143.33566.7359May 31, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Opus-4.6 (1M)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0586.67
Official Instruct ModelProtocol=Official Instruct, Backbone=SmolLM3-3B2026.0584
GLM-4.7 & ANDES (Ours)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.0578.67
Opus-4.6Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0575.92
GLM-4.7 (Scaffold-only)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.0570
Opus-4.7 (xHigh)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0562.33
GPT-5.2Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0533.33
GPT-5.4 (High)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0529.67
Gemini-3.1-ProProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0527.67
Base Model (SmolLM3-3B)Protocol=Zero-Shot, Backbone=SmolLM3-3B2026.050
Sonnet-4.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
Qwen3-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
Kimi-K2-ThinkingProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
MiniMax-M2.1Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
GPT-5.1-Codex-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
MiniMax-M2.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
GLM-4.7 (OpenCode)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.050