Rhetorical Role Labeling on LEGALEVAL (test) benchmark leaderboard · SOTA2 Research

Rhetorical Role Labeling on LEGALEVAL (test)

0.6297Micro-F1Mistral-7B

Evaluation Results

Method	Links
Mistral-7B2026.05		0.6297	0.7393
Llama-3-8B2026.05		0.6116	0.7443
RoBERTa_base2026.05		0.607	0.7321
Qwen-3-8B2026.05		0.6025	0.7306
Mistral-7B2026.05		0.6007	0.7163
Llama-3-8B2026.05		0.6001	0.732
DeBERTa_base2026.05		0.5995	0.7375
BERT_base2026.05		0.5912	0.7006
Qwen-3-8B2026.05		0.5887	0.7119
RoBERTa_base2026.05		0.5768	0.7212
DeBERTa_base2026.05		0.5676	0.725
ALBERT_base2026.05		0.567	0.6845
BERT_base2026.05		0.5548	0.6892
ALBERT_base2026.05		0.5516	0.6789