List your company
ResearchFormerly WizWand

General Classification on Banking77 (test)

79.62Macro F1EvoPool
0.78821.25441.7262.186Jun 1, 2026
Updated 5mo ago

Evaluation results

MethodLinks
EvoPoolDownstream Model=Llama, CFT=true2026.0679.62
EvoPoolBackbone=Llama-3.1-8B2026.0679.62
LLM-AnnotationBackbone=Llama-3.1-8B2026.0679.15
EvoPoolDownstream Model=Qwen, CFT=true2026.0676.61
EvoPoolBackbone=Qwen2-1.5B2026.0676.61
Self-TrainDownstream Model=RoBERTa-large2026.0676.07
EvoPoolDownstream Model=RoB, CFT=true2026.0675.2
EvoPoolBackbone=RoBERTa-large2026.0675.2
LLM-AnnotationBackbone=Qwen2-1.5B2026.0673.98
LLM-AnnotationBackbone=RoBERTa-large2026.0673.76
EvoPoolDownstream Model=RoB, CFT=false2026.0673.32
EvoPoolDownstream Model=RoBERTa-large2026.0673.32
EvoPoolDownstream Model=Llama, CFT=false2026.0672.41
EvoPoolDownstream Model=Llama-3.1-8B2026.0672.41
EvoPoolDownstream Model=Qwen, CFT=false2026.0671.5
EvoPoolDownstream Model=Qwen3-1.7B2026.0671.5
EvoPoolBackbone=gpt-4o-mini2026.0670.23
LLM-AnnotationDownstream Model=RoBERTa-large2026.0665.5
HumanDownstream Model=Llama, CFT=true2026.0664.71
LLM-AnnotationDownstream Model=Llama-3.1-8B2026.0664.1
Self-TrainDownstream Model=Llama-3.1-8B2026.0663.71
LLM-AnnotationDownstream Model=Qwen3-1.7B2026.0663.61
LLM annotationBackbone=gpt-4o-mini2026.0662.61
LLM-EvalDownstream Model=RoBERTa-large2026.0662.61
LLM-EvalDownstream Model=Qwen3-1.7B2026.0662.61
LLM-EvalDownstream Model=Llama-3.1-8B2026.0662.61
HumanDownstream Model=RoB, CFT=true2026.0656.96
GoldenDownstream Model=Llama-3.1-8B2026.0651.17
HumanDownstream Model=Qwen, CFT=true2026.0648.31
GoldenDownstream Model=RoBERTa-large2026.0643.3
HumanDownstream Model=RoB, CFT=false2026.0639.86
HumanDownstream Model=Llama, CFT=false2026.0639.41
DataSculptBackbone=Llama-3.1-8B2026.0637.15
HumanDownstream Model=Qwen, CFT=false2026.0635.2
DataSculptBackbone=RoBERTa-large2026.0635.15
AlchemistBackbone=RoBERTa-large2026.0627.59
AlchemistBackbone=Llama-3.1-8B2026.0626.78
Self-TrainDownstream Model=Qwen3-1.7B2026.0612.2
DataSculptDownstream Model=RoBERTa-large2026.069.29
DataSculptBackbone=gpt-4o-mini2026.068.24
DataSculptBackbone=Qwen2-1.5B2026.067.87
DataSculptDownstream Model=Llama-3.1-8B2026.067.13
AlchemistBackbone=Qwen2-1.5B2026.066.82
GoldenDownstream Model=Qwen3-1.7B2026.066.79
DataSculptDownstream Model=Qwen3-1.7B2026.065.4
AlchemistDownstream Model=RoBERTa-large2026.064.91
AlchemistDownstream Model=Llama-3.1-8B2026.064.76
AlchemistDownstream Model=Qwen3-1.7B2026.064.43
AlchemistBackbone=gpt-4o-mini2026.063.82