# LPS (FinancialPhraseBank) Benchmark Scores & Performance

> LPS (FinancialPhraseBank) has published results in 2 original benchmark tables. The evaluated configuration, source metrics, and precision remain visible below. These results do not produce a general model score or rank.

Canonical page: https://benchlm.ai/models/native-financialphrasebank-lps

Last updated: 2026-10-01

General benchmark catalog last updated: October 1, 2026. This profile’s source review has its own date above.

## Model Details

| Property | Value |
|----------|-------|
| Creator | Malo et al. |
| Source Type | Research system |
| Reasoning Type | Unspecified |
| Context Window | Not established by evaluation |
| Official model card | [Benchmark-owner results and configuration](https://arxiv.org/abs/1307.5336) |
| Overall Score | Not computed (source protocol results only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: LPS (FinancialPhraseBank)
- Variant: benchmark-system
- Benchmarks covered: 0 of 645
- Coverage note: Original benchmark result tables appear below; these metrics are separate from weighted benchmark slots.

## Original benchmark results

[All model results (JSON)](/api/data/benchmarks?model=native-financialphrasebank-lps) · [Numeric metrics (CSV)](/api/data/benchmarks?model=native-financialphrasebank-lps&format=csv)

### Class metrics at 100% and >75% agreement

The original study reports ten-fold cross-validation at four annotator-agreement thresholds. Its class-specific accuracy, precision, recall, and F1 are ratios from 0 to 1. These are not overall sentiment accuracy or Perplexity’s sampled panel. No unified modern leaderboard is published in the reviewed benchmark-owner sources.

All metrics are 0–1 ratios. SVM-MPQA is the paper’s baseline marked with footnote a.

Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts — Pekka Malo and colleagues. Numeric results transcribed and reformatted; evaluation notes and model links added by BenchLM. Published numeric precision is retained.

[Published source](https://arxiv.org/abs/1307.5336) · [Full FinancialPhraseBank results](/benchmarks/financialphrasebank)

| Agreement | Class | Metric | LPS |
| --- | --- | --- | --- |
| 100% | Positive | Accuracy | 0.869 |
| 100% | Positive | Recall | 0.737 |
| 100% | Positive | Precision | 0.742 |
| 100% | Positive | F1-score | 0.739 |
| 100% | Neutral | Accuracy | 0.828 |
| 100% | Neutral | Recall | 0.868 |
| 100% | Neutral | Precision | 0.854 |
| 100% | Neutral | F1-score | 0.861 |
| 100% | Negative | Accuracy | 0.951 |
| 100% | Negative | Recall | 0.789 |
| 100% | Negative | Precision | 0.839 |
| 100% | Negative | F1-score | 0.813 |
| >75% | Positive | Accuracy | 0.836 |
| >75% | Positive | Recall | 0.658 |
| >75% | Positive | Precision | 0.690 |
| >75% | Positive | F1-score | 0.674 |
| >75% | Neutral | Accuracy | 0.792 |
| >75% | Neutral | Recall | 0.837 |
| >75% | Neutral | Precision | 0.830 |
| >75% | Neutral | F1-score | 0.833 |
| >75% | Negative | Accuracy | 0.945 |
| >75% | Negative | Recall | 0.800 |
| >75% | Negative | Precision | 0.760 |
| >75% | Negative | F1-score | 0.780 |

### Class metrics at >66% and >50% agreement

The original study reports ten-fold cross-validation at four annotator-agreement thresholds. Its class-specific accuracy, precision, recall, and F1 are ratios from 0 to 1. These are not overall sentiment accuracy or Perplexity’s sampled panel. No unified modern leaderboard is published in the reviewed benchmark-owner sources.

All metrics are 0–1 ratios. SVM-MPQA is the paper’s baseline marked with footnote a.

Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts — Pekka Malo and colleagues. Numeric results transcribed and reformatted; evaluation notes and model links added by BenchLM. Published numeric precision is retained.

[Published source](https://arxiv.org/abs/1307.5336) · [Full FinancialPhraseBank results](/benchmarks/financialphrasebank)

| Agreement | Class | Metric | LPS |
| --- | --- | --- | --- |
| >66% | Positive | Accuracy | 0.798 |
| >66% | Positive | Recall | 0.816 |
| >66% | Positive | Precision | 0.599 |
| >66% | Positive | F1-score | 0.691 |
| >66% | Neutral | Accuracy | 0.753 |
| >66% | Neutral | Recall | 0.705 |
| >66% | Neutral | Precision | 0.858 |
| >66% | Neutral | F1-score | 0.774 |
| >66% | Negative | Accuracy | 0.937 |
| >66% | Negative | Recall | 0.768 |
| >66% | Negative | Precision | 0.729 |
| >66% | Negative | F1-score | 0.748 |
| >50% | Positive | Accuracy | 0.786 |
| >50% | Positive | Recall | 0.535 |
| >50% | Positive | Precision | 0.645 |
| >50% | Positive | F1-score | 0.585 |
| >50% | Neutral | Accuracy | 0.735 |
| >50% | Neutral | Recall | 0.809 |
| >50% | Neutral | Precision | 0.760 |
| >50% | Neutral | F1-score | 0.784 |
| >50% | Negative | Accuracy | 0.933 |
| >50% | Negative | Recall | 0.772 |
| >50% | Negative | Precision | 0.716 |
| >50% | Negative | F1-score | 0.743 |

## Other Malo et al. Models

- [R-LPS (FinancialPhraseBank)](/models/native-financialphrasebank-r-lps) - Score: not computed
- [SVM-MPQA (FinancialPhraseBank)](/models/native-financialphrasebank-svm-mpqa) - Score: not computed
- [W-Loughran (FinancialPhraseBank)](/models/native-financialphrasebank-w-loughran) - Score: not computed
- [W-MPQA (FinancialPhraseBank)](/models/native-financialphrasebank-w-mpqa) - Score: not computed