List your company

Instruction Following on ComplexInstruct Level 1

0.982ISRDVRws
0.761520.818760.8760.93324Oct 16, 2024

Evaluation results

MethodLinks
DVRwsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, warm-start=true2024.100.982
CRITICBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.981
DVRcsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, cold-start=true2024.100.98
ReActBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.975
R-SampleBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.973
U-SCBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.96
VanillaBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.955
DVRBackbone=Llama-3-8B-Instruct, Start Type=Warm-Start2024.100.954
GPT-4-turboEvaluation Protocol=zero-shot2024.100.953
ReflexionBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.953
DVRBackbone=Llama3.1-8B, Evaluation Protocol=zero-shot2024.100.952
DVRBackbone=Mistral-7B, Evaluation Protocol=zero-shot2024.100.95
DVRBackbone=Llama-3-8B-Instruct, Start Type=Cold-Start2024.100.95
BSMBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.95
CRITICBackbone=Llama-3-8B-Instruct2024.100.941
ReActBackbone=Llama-3-8B-Instruct2024.100.936
R-SampleBackbone=Llama-3-8B-Instruct2024.100.908
Llama3.1-8BEvaluation Protocol=zero-shot2024.100.905
U-SCBackbone=Llama-3-8B-Instruct2024.100.895
BSMBackbone=Llama-3-8B-Instruct2024.100.892
VanillaBackbone=Llama-3-8B-Instruct2024.100.891
ReflexionBackbone=Llama-3-8B-Instruct2024.100.888
Mistral-7BEvaluation Protocol=zero-shot2024.100.77