
FinBERT
The standard BERT-based model for financial sentiment analysis.
About
FinBERT (ProsusAI/finbert) is a BERT model further pretrained on a large financial corpus (Reuters TRC2) and fine-tuned on the Financial PhraseBank for three-way sentiment classification of financial text: positive, neutral, negative. Published in 2019, it became the default baseline for finance NLP, widely reported to beat general models on financial sentiment benchmarks.
A decade-old architecture by current standards, it remains in heavy practical use for earnings-call analysis, headline scoring, and market-signal pipelines because it is small, fast, and well understood. The Hugging Face release is the canonical checkpoint most downstream work builds on.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 7/10
Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 109; Trending score 68/100 from researcher assessment.