List your company

Instruction Following on Collie (Out-of-Domain)

52.4Average ScoreQwQ-32B
11.42422.06232.743.338Oct 16, 2025

Evaluation results

MethodLinks
QwQ-32BBase Model=Qwen-32B2025.1052.4
Llama-3.1-8B-Instruct-IFBase Model=LLaMA-8B2025.1050.2
GPT-4oBase Model=GPT2025.1049.8
Qwen2.5-32B-Instruct-IFBase Model=Qwen-32B2025.1048.1
Llama-3.1-8B-InstructBase Model=LLaMA-8B2025.1046.5
Qwen2.5-32B-InstructBase Model=Qwen-32B2025.1043.3
Qwen2.5-7B-Instruct-IFBase Model=Qwen-7B2025.1038
Distill-Qwen-14B-IFBase Model=Qwen-14B2025.1037.6
R1-0528-Qwen3-8BBase Model=Qwen-8B2025.1037.1
R1-0528-Qwen3-8BBase Model=Qwen-8B2025.1036.9
Qwen2.5-7B-InstructBase Model=Qwen-7B2025.1036.3
Distill-Qwen-14BBase Model=Qwen-14B2025.1034.4
VERIF-8BBase Model=LLaMA-8B2025.1028.3
SPAR-8B-DPOBase Model=LLaMA-8B2025.1027.7
Distill-Qwen-7B-IFBase Model=Qwen-7B2025.1027
Distill-Qwen-7BBase Model=Qwen-7B2025.1025.2
Crab-7B-DPOBase Model=Mistral-7B2025.1019.6
Conifer-7B-DPOBase Model=Mistral-7B2025.1017.8
Qwen2.5-1.5B-Instruct-IFBase Model=Qwen-1.5B2025.1016.7
IR-1.5BBase Model=Qwen-1.5B2025.1016.3
Distill-Qwen-1.5B-IFBase Model=Qwen-1.5B2025.1014.5
Distill-Qwen-1.5BBase Model=Qwen-1.5B2025.1014
Qwen2.5-1.5B-InstructBase Model=Qwen-1.5B2025.1013