General classification on AGNews (test)
90.16Macro F1Golden
Evaluation results
| Method | Links | |
|---|---|---|
| GoldenDownstream Model=RoBERTa-large2026.06 | 90.16 | |
| LLM-AnnotationBackbone=Llama-3.1-8B2026.06 | 89.56 | |
| EvoPoolBackbone=Qwen2-1.5B2026.06 | 89.55 | |
| EvoPoolDownstream Model=Qwen3-1.7B2026.06 | 89.51 | |
| LLM-AnnotationBackbone=RoBERTa-large2026.06 | 89.48 | |
| DataSculptBackbone=RoBERTa-large2026.06 | 89.27 | |
| LLM-AnnotationBackbone=Qwen2-1.5B2026.06 | 89.26 | |
| Self-TrainDownstream Model=RoBERTa-large2026.06 | 89.25 | |
| EvoPoolBackbone=Llama-3.1-8B2026.06 | 88.99 | |
| EvoPoolDownstream Model=RoBERTa-large2026.06 | 88.6 | |
| EvoPoolDownstream Model=Llama-3.1-8B2026.06 | 88.59 | |
| EvoPoolBackbone=RoBERTa-large2026.06 | 88.42 | |
| Self-TrainDownstream Model=Llama-3.1-8B2026.06 | 88.03 | |
| DataSculptBackbone=Qwen2-1.5B2026.06 | 87.65 | |
| LLM-AnnotationDownstream Model=RoBERTa-large2026.06 | 87.46 | |
| LLM-AnnotationDownstream Model=Llama-3.1-8B2026.06 | 87.35 | |
| DataSculptBackbone=Llama-3.1-8B2026.06 | 87.11 | |
| AlchemistBackbone=Llama-3.1-8B2026.06 | 87.05 | |
| LLM-AnnotationDownstream Model=Qwen3-1.7B2026.06 | 87.01 | |
| GoldenDownstream Model=Llama-3.1-8B2026.06 | 86.58 | |
| EvoPoolBackbone=gpt-4o-mini2026.06 | 86.42 | |
| LLM annotationBackbone=gpt-4o-mini2026.06 | 86.28 | |
| LLM-EvalDownstream Model=RoBERTa-large2026.06 | 86.28 | |
| LLM-EvalDownstream Model=Qwen3-1.7B2026.06 | 86.28 | |
| LLM-EvalDownstream Model=Llama-3.1-8B2026.06 | 86.28 | |
| Self-TrainDownstream Model=Qwen3-1.7B2026.06 | 85.88 | |
| AlchemistBackbone=RoBERTa-large2026.06 | 85.79 | |
| GoldenDownstream Model=Qwen3-1.7B2026.06 | 84.22 | |
| AlchemistBackbone=Qwen2-1.5B2026.06 | 83.07 | |
| DataSculptDownstream Model=RoBERTa-large2026.06 | 82.22 | |
| DataSculptDownstream Model=Qwen3-1.7B2026.06 | 79.22 | |
| DataSculptDownstream Model=Llama-3.1-8B2026.06 | 72.48 | |
| AlchemistDownstream Model=RoBERTa-large2026.06 | 57.32 | |
| AlchemistDownstream Model=Qwen3-1.7B2026.06 | 55.41 | |
| AlchemistDownstream Model=Llama-3.1-8B2026.06 | 52.98 | |
| DataSculptBackbone=gpt-4o-mini2026.06 | 49.94 | |
| AlchemistBackbone=gpt-4o-mini2026.06 | 46.68 |