List your company

Instruction Following on ComplexInstruct Level 5

0.76ISRDVRws
0.098560.270280.4420.61372Oct 16, 2024

Evaluation results

MethodLinks
DVRwsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, warm-start=true2024.100.76
DVRcsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, cold-start=true2024.100.757
CRITICBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.737
ReActBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.65
R-SampleBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.638
DVRBackbone=Llama3.1-8B, Evaluation Protocol=zero-shot2024.100.605
DVRBackbone=Llama-3-8B-Instruct, Start Type=Warm-Start2024.100.554
GPT-4-turboEvaluation Protocol=zero-shot2024.100.537
DVRBackbone=Llama-3-8B-Instruct, Start Type=Cold-Start2024.100.537
U-SCBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.525
ReflexionBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.516
VanillaBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.513
CRITICBackbone=Llama-3-8B-Instruct2024.100.511
BSMBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.100.496
R-SampleBackbone=Llama-3-8B-Instruct2024.100.398
ReActBackbone=Llama-3-8B-Instruct2024.100.391
DVRBackbone=Mistral-7B, Evaluation Protocol=zero-shot2024.100.364
Llama3.1-8BEvaluation Protocol=zero-shot2024.100.356
U-SCBackbone=Llama-3-8B-Instruct2024.100.312
VanillaBackbone=Llama-3-8B-Instruct2024.100.304
ReflexionBackbone=Llama-3-8B-Instruct2024.100.3
BSMBackbone=Llama-3-8B-Instruct2024.100.288
Mistral-7BEvaluation Protocol=zero-shot2024.100.124