Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Sentiment Analysis On Dynasent

Metrics

Macro F1

Results

Performance results of various models on this benchmark

Model Name	Macro F1	Paper Title	Repository
GPT-4o + ELECTRA Large FT (Prompt, Label, Examples)	81.53	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
ELECTRA Large Fine-Tuned	76.29	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o-mini + ELECTRA Large FT (Prompt, Label)	77.94	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o + ELECTRA Large FT	77.69	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
ELECTRA Base Fine-Tuned	71.83	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
SVM	-	Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM
GPT-4o Fine-Tuned (Minimal)	89	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o-mini + ELECTRA Large FT (Prompt, Label, Probabilities)	79.72	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o-mini + ELECTRA Base FT	76.19	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o-mini Fine-Tuned	86.9	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o (Prompt)	80.22	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
GPT-4o-mini (Prompt)	77.35	ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis

0 of 12 row(s) selected.