Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bi, Ziqian, Zhang, Danyang, Song, Junhao, Tseng, Chiung-Yi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915680387858432
author Bi, Ziqian
Zhang, Danyang
Song, Junhao
Tseng, Chiung-Yi
author_facet Bi, Ziqian
Zhang, Danyang
Song, Junhao
Tseng, Chiung-Yi
contents The rapid adoption of large language models in financial services necessitates rigorous evaluation frameworks to assess their performance, efficiency, and practical applicability. This paper conducts a comprehensive evaluation of the GPT-OSS model family alongside contemporary LLMs across ten diverse financial NLP tasks. Through extensive experimentation on 120B and 20B parameter variants of GPT-OSS, we reveal a counterintuitive finding: the smaller GPT-OSS-20B model achieves comparable accuracy (65.1% vs 66.5%) while demonstrating superior computational efficiency with 198.4 Token Efficiency Score and 159.80 tokens per second processing speed [1]. Our evaluation encompasses sentiment analysis, question answering, and entity recognition tasks using real-world financial datasets including Financial PhraseBank, FiQA-SA, and FLARE FINERORD. We introduce novel efficiency metrics that capture the trade-off between model performance and resource utilization, providing critical insights for deployment decisions in production environments. The benchmark reveals that GPT-OSS models consistently outperform larger competitors including Qwen3-235B, challenging the prevailing assumption that model scale directly correlates with task performance [2]. Our findings demonstrate that architectural innovations and training strategies in GPT-OSS enable smaller models to achieve competitive performance with significantly reduced computational overhead, offering a pathway toward sustainable and cost-effective deployment of LLMs in financial applications.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14717
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox
Bi, Ziqian
Zhang, Danyang
Song, Junhao
Tseng, Chiung-Yi
Machine Learning
The rapid adoption of large language models in financial services necessitates rigorous evaluation frameworks to assess their performance, efficiency, and practical applicability. This paper conducts a comprehensive evaluation of the GPT-OSS model family alongside contemporary LLMs across ten diverse financial NLP tasks. Through extensive experimentation on 120B and 20B parameter variants of GPT-OSS, we reveal a counterintuitive finding: the smaller GPT-OSS-20B model achieves comparable accuracy (65.1% vs 66.5%) while demonstrating superior computational efficiency with 198.4 Token Efficiency Score and 159.80 tokens per second processing speed [1]. Our evaluation encompasses sentiment analysis, question answering, and entity recognition tasks using real-world financial datasets including Financial PhraseBank, FiQA-SA, and FLARE FINERORD. We introduce novel efficiency metrics that capture the trade-off between model performance and resource utilization, providing critical insights for deployment decisions in production environments. The benchmark reveals that GPT-OSS models consistently outperform larger competitors including Qwen3-235B, challenging the prevailing assumption that model scale directly correlates with task performance [2]. Our findings demonstrate that architectural innovations and training strategies in GPT-OSS enable smaller models to achieve competitive performance with significantly reduced computational overhead, offering a pathway toward sustainable and cost-effective deployment of LLMs in financial applications.
title Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox
topic Machine Learning
url https://arxiv.org/abs/2512.14717