List your company

Tool Use on APT-Bench

65.8AccuracyQwen3
56.33658.79361.2563.707Dec 31, 2025

Evaluation results

MethodLinks
Qwen3Parameters=4B, Variant=Base2025.1265.8
Youtu-LLMParameters=2B, Variant=Base2025.1264.2
Llama3.1Parameters=8B, Variant=Base2025.1264.1
Gemma3Parameters=4B, Variant=Base2025.1261.7
SmolLM3Parameters=3B, Variant=Base2025.1259.1
Qwen3Parameters=1.7B, Variant=Base2025.1256.7