List your company

Tool Retrieval on TOOLRET Zero-Shot Custom

45.8nDCG@10TOOLQP
25.62430.86236.141.338Jan 12, 2026

Evaluation results

MethodLinks
TOOLQPMethod Category=Fine-tuning, Training Data Size=10k, Backbone Model=1.7B2026.0145.843
HyDE/PRFMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0141.626.7
Q2P/SFTMethod Category=Fine-tuning, Training Data Size=10k, Backbone Model=1.5B/1.7B models2026.0139.735.6
bge-gemmaMethod Category=Re-ranking with cross-encoder2026.0139.436.2
gte-Qwen/ContrastiveFTMethod Category=Fine-tuning, Training Data Size=10k, Backbone Model=1.5B/1.7B models2026.0139.235.5
Q2E/ZSMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0138.735.7
Q2D/PRFMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.013733.7
Re-InvokeMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0136.831.7
Base Retriever (gte-Qwen)Method Category=Base Retriever2026.0135.632.4
Q2E/PRFMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0135.333.3
Q2D/ZSMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0133.333.5
D2QMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0133.330.8
bge-m3Method Category=Re-ranking with cross-encoder2026.0132.930.2
TOOLQP-FORMATMethod Category=Fine-tuning, Training Data Size=10k, Backbone Model=1.7B2026.0132.230.1
HyDE/ZSMethod Category=Prompting, Backbone Model=Qwen3-30B-A3B-Instruct2026.0126.429.7