List your company

Tool Use on Unified evaluation benchmark D Single-Turn (test)

93SPUniToolCall
45.1657.587082.42Apr 13, 2026

Evaluation results

MethodLinks
UniToolCallSetting=Hybrid-20 Setting2026.049393.831.652.4
Qwen3-8B (Upper Bound)Setting=GT Setting2026.0492.695.532.154.9
Qwen3-32BSetting=Hybrid-20 Setting2026.0472.774.327.947.4
Gemini 3 Flash PreviewSetting=Hybrid-20 Setting2026.0470.370.930.350.5
Qwen3-8B (Vanilla)Setting=Hybrid-20 Setting2026.0463.366.522.122.1
Claude 4.6 SonnetSetting=Hybrid-20 Setting2026.0462.162.730.347.9
Kimi-K2-InstructSetting=Hybrid-20 Setting2026.0458.759.726.542
GPT-5.2 InstantSetting=Hybrid-20 Setting2026.0450.552.526.341.5
DeepSeek-V3.2Setting=Hybrid-20 Setting2026.044749.622.936.3