Skip to content
← Models
Open weightsProsusAI/10 trustMetrics-checked
FinBERT logo

FinBERT

The standard BERT-based model for financial sentiment analysis.

Visit official page →

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

Open weights

Released

August 1, 2019

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

financial-sentiment-analysisearnings-call-analysismarket-signal-pipelines

Trust score — 7/10

/10 trustMetrics-checked

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.

Sources