{"paper_id":"2409.13749","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","authors":["Neel Rajani","Lilli Kiessling","Aleksandr Ogaltsov","Claus Lang"],"paper_date":"2024-09-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.13749v1","page_url":"https://thequant.space/flowcharts/kodexv0.1-a-family-of-state-of-the-art-financial-large-lang/","scores":{"empirical_rigor":8,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes KodeXv0.1, a family of financial large language models fine‑tuned on synthetic data to outperform GPT‑4 on financial QA.","quote":"We introduce KodeXv0.1, a family of large language models that outclass GPT-4 in financial question answering.","summary":"Although powerful, current cutting-edge LLMs may not fulfil the needs of highly specialised sectors. We introduce KodeXv0.1, a family of large language models that outclass GPT-4 in financial question answering. We utilise the base variants of Llama 3.1 8B and 70B and adapt them to the financial…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"Synthetic Context‑Question‑Answer dataset","provider":"publicly available financial documents (earnings calls, busi","kind":"synthetic","access":"public","period":null,"universe":"822 documents from over 40 companies listed on major indices such as the MSCI World and Eu","quote":"A total of 822 documents from over 40 companies were utilized to generate the training dataset."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"KodeX‑8Bv0.1 exceeds other instruct variants in the same parameter regime by up to 9.27 percentage points and beats GPT‑4 by 1.01% on the withheld test set.","kind":"performance","quote":"The score of KodeX-8Bv0.1 exceeds that of instruct variants of Mistral and Llama 3.1 in the same parameter regime by up to 9.27 percentage points, and exceeds that of Llama 3.1-70B-instruct and GPT-4 by 3.78% and 1.01%, respectively."},{"finding":"KodeX‑70Bv0.1 outperforms GPT‑4 on FinanceBench by 1.93 percentage points, setting state‑of‑the‑art results across all tested benchmarks.","kind":"performance","quote":"KodeX-70Bv0.1, which even outperforms GPT-4 by 1.93 percentage points."},{"finding":"Across all benchmarks (FinanceBench, FinQABench, and a withheld test split), KodeXv0.1 models achieve the highest scores, establishing new state‑of‑the‑art performance.","kind":"performance","quote":"Our KodeXv0.1 models set the state of the art in all benchmarks that we tested."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":10,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:02:15Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}