List your company

Tool selection on SD Single-domain

94.04AccuracyMTA
18.140837.845457.5577.2546Jan 19, 2026

Evaluation results

MethodLinks
MTABackbone=Qwen1.5-Chat (7B)2026.0194.04
FTBackbone=Qwen1.5-Chat (7B)2026.0192.31
MTABackbone=Baichuan2-Chat (7B)2026.0192
FTBackbone=Baichuan2-Chat (7B)2026.0188.49
MTABackbone=Chinese Alpaca-2 (7B)2026.0187.92
MTABackbone=ChatGLM3 (6B)2026.0183.68
FTBackbone=Chinese Alpaca-2 (7B)2026.0181.98
FTBackbone=ChatGLM3 (6B)2026.0178.68
ReActBackbone=Qwen1.5-Chat (7B)2026.0146.82
ReActBackbone=ChatGLM3 (6B)2026.0140.68
BaseBackbone=Qwen1.5-Chat (7B)2026.0137.74
ReActBackbone=Baichuan2-Chat (7B)2026.0137.36
CoTBackbone=Qwen1.5-Chat (7B)2026.0136.82
CoTBackbone=ChatGLM3 (6B)2026.0136.27
BaseBackbone=ChatGLM3 (6B)2026.0135.35
BaseBackbone=Baichuan2-Chat (7B)2026.0134.2
BaseBackbone=Chinese Alpaca-2 (7B)2026.0128.7
CoTBackbone=Baichuan2-Chat (7B)2026.0127.19
ReActBackbone=Chinese Alpaca-2 (7B)2026.0121.11
CoTBackbone=Chinese Alpaca-2 (7B)2026.0121.06