List your company

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

8.3SP ScoreQwen3-32B
-0.3321.9094.156.391Apr 13, 2026

Evaluation results

MethodLinks
Qwen3-32BSetting=Hybrid-20 Setting2026.048.338.221.628.8
Qwen3-8B (Upper Bound)Setting=GT Setting2026.04039.518.824.9
GPT-5.2 InstantSetting=Hybrid-20 Setting2026.04016.19.19.8
Gemini 3 Flash PreviewSetting=Hybrid-20 Setting2026.04022.514.215.6
Claude 4.6 SonnetSetting=Hybrid-20 Setting2026.04034.819.425.2
Kimi-K2-InstructSetting=Hybrid-20 Setting2026.04031.118.424.9
DeepSeek-V3.2Setting=Hybrid-20 Setting2026.0401510.313
Qwen3-8B (Vanilla)Setting=Hybrid-20 Setting2026.04025.812.112.1
UniToolCallSetting=Hybrid-20 Setting2026.04039.421.226.1