List your company

Complex reasoning on VitaminC (test)

78.4Macro-F1EvoPool
1.783221.674141.56561.4559Jun 1, 2026

Evaluation results

MethodLinks
EvoPoolBackbone=Llama-3.1-8B2026.0678.4
LLM-AnnotationBackbone=Llama-3.1-8B2026.0678.05
LLM-AnnotationBackbone=Qwen2-1.5B2026.0674.11
EvoPoolBackbone=Qwen2-1.5B2026.0673.83
AlchemistBackbone=Qwen2-1.5B2026.0672.67
LLM-AnnotationBackbone=RoBERTa-large2026.0670.97
EvoPoolBackbone=RoBERTa-large2026.0670.38
EvoPoolDownstream Model=Llama-3.1-8B2026.0667.97
EvoPoolBackbone=gpt-4o-mini2026.0666.67
EvoPoolDownstream Model=Qwen3-1.7B2026.0666.59
LLM-AnnotationDownstream Model=Qwen3-1.7B2026.0665.62
LLM-AnnotationDownstream Model=Llama-3.1-8B2026.0665.08
LLM annotationBackbone=gpt-4o-mini2026.0664.82
LLM-EvalDownstream Model=RoBERTa-large2026.0664.82
LLM-EvalDownstream Model=Qwen3-1.7B2026.0664.82
LLM-EvalDownstream Model=Llama-3.1-8B2026.0664.82
EvoPoolDownstream Model=RoBERTa-large2026.0664.76
LLM-AnnotationDownstream Model=RoBERTa-large2026.0659.19
DataSculptBackbone=Qwen2-1.5B2026.0653.66
Self-TrainDownstream Model=RoBERTa-large2026.0652.82
Self-TrainDownstream Model=Qwen3-1.7B2026.0651.74
GoldenDownstream Model=Qwen3-1.7B2026.0650.65
Self-TrainDownstream Model=Llama-3.1-8B2026.0647.84
AlchemistBackbone=Llama-3.1-8B2026.0646.42
GoldenDownstream Model=RoBERTa-large2026.0645.43
GoldenDownstream Model=Llama-3.1-8B2026.0644.81
DataSculptBackbone=Llama-3.1-8B2026.0643.19
DataSculptBackbone=RoBERTa-large2026.0639.97
DataSculptDownstream Model=RoBERTa-large2026.0626.46
DataSculptDownstream Model=Llama-3.1-8B2026.0626
DataSculptDownstream Model=Qwen3-1.7B2026.0622.57
AlchemistBackbone=gpt-4o-mini2026.0616.81
AlchemistBackbone=RoBERTa-large2026.0616.67
AlchemistDownstream Model=RoBERTa-large2026.0616.67
AlchemistDownstream Model=Qwen3-1.7B2026.0616.67
AlchemistDownstream Model=Llama-3.1-8B2026.0616.67
DataSculptBackbone=gpt-4o-mini2026.064.73