List your company

Multi-label biomedical classification on Ohsumed (test)

63.75Macro F1EvoPool
-2.113214.985932.08549.1841Jun 1, 2026

Evaluation results

MethodLinks
EvoPoolBackbone=Llama-3.1-8B2026.0663.75
EvoPoolBackbone=RoBERTa-large2026.0661.31
EvoPoolBackbone=Qwen2-1.5B2026.0661.11
LLM-AnnotationBackbone=Llama-3.1-8B2026.0656.36
EvoPoolDownstream Model=Llama-3.1-8B2026.0655.66
EvoPoolDownstream Model=RoBERTa-large2026.0655.65
EvoPoolDownstream Model=Qwen3-1.7B2026.0654.73
LLM-AnnotationBackbone=RoBERTa-large2026.0654.42
EvoPoolBackbone=gpt-4o-mini2026.0654.2
LLM-AnnotationBackbone=Qwen2-1.5B2026.0653.16
LLM-AnnotationDownstream Model=Llama-3.1-8B2026.0647.26
LLM-AnnotationDownstream Model=Qwen3-1.7B2026.0646.34
LLM-AnnotationDownstream Model=RoBERTa-large2026.0645.66
LLM annotationBackbone=gpt-4o-mini2026.0644.33
LLM-EvalDownstream Model=RoBERTa-large2026.0644.33
LLM-EvalDownstream Model=Qwen3-1.7B2026.0644.33
LLM-EvalDownstream Model=Llama-3.1-8B2026.0644.33
DataSculptBackbone=Llama-3.1-8B2026.0626.61
Self-TrainDownstream Model=RoBERTa-large2026.0625.26
AlchemistBackbone=Llama-3.1-8B2026.0623.35
AlchemistBackbone=Qwen2-1.5B2026.0620.71
DataSculptBackbone=Qwen2-1.5B2026.0620.51
AlchemistBackbone=RoBERTa-large2026.0620.12
AlchemistDownstream Model=Qwen3-1.7B2026.0620.12
AlchemistDownstream Model=Llama-3.1-8B2026.0620.06
DataSculptBackbone=RoBERTa-large2026.0620.02
AlchemistDownstream Model=RoBERTa-large2026.0619.4
AlchemistBackbone=gpt-4o-mini2026.0619.01
Self-TrainDownstream Model=Llama-3.1-8B2026.0618.69
DataSculptBackbone=gpt-4o-mini2026.067.38
DataSculptDownstream Model=RoBERTa-large2026.067.13
DataSculptDownstream Model=Llama-3.1-8B2026.066.92
DataSculptDownstream Model=Qwen3-1.7B2026.066.85
GoldenDownstream Model=RoBERTa-large2026.066.71
Self-TrainDownstream Model=Qwen3-1.7B2026.066.52
GoldenDownstream Model=Llama-3.1-8B2026.065.3
GoldenDownstream Model=Qwen3-1.7B2026.060.42