{"id":"https://openalex.org/W7154720468","doi":"https://doi.org/10.48550/arxiv.2604.14199","title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","display_name":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7154720468","doi":"https://doi.org/10.48550/arxiv.2604.14199"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.14199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.14199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133899672","display_name":"Pu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cheng, Pu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101415161","display_name":"Juncheng Liu","orcid":"https://orcid.org/0000-0002-5895-0581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Juncheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017229118","display_name":"Yunshen Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Yunshen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133899672"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.7957000136375427,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.7957000136375427,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.03310000151395798,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.0284000001847744,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5694000124931335},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5501999855041504},{"id":"https://openalex.org/keywords/sharpe-ratio","display_name":"Sharpe ratio","score":0.5403000116348267},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5394999980926514},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/financial-market","display_name":"Financial market","score":0.40139999985694885},{"id":"https://openalex.org/keywords/market-timing","display_name":"Market timing","score":0.3898000121116638},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.3882000148296356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5800999999046326},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C139938925","wikidata":"https://www.wikidata.org/wiki/Q1501898","display_name":"Sharpe ratio","level":3,"score":0.5403000116348267},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C118315980","wikidata":"https://www.wikidata.org/wiki/Q375350","display_name":"Market timing","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C199728807","wikidata":"https://www.wikidata.org/wiki/Q2578557","display_name":"Equity (law)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C2779309563","wikidata":"https://www.wikidata.org/wiki/Q649206","display_name":"Order book","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.32820001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C122282355","wikidata":"https://www.wikidata.org/wiki/Q7246855","display_name":"Probabilistic forecasting","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C114118609","wikidata":"https://www.wikidata.org/wiki/Q3036837","display_name":"Market data","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C103659442","wikidata":"https://www.wikidata.org/wiki/Q1662488","display_name":"Information ratio","level":4,"score":0.25760000944137573},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.14199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.14199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.7093660235404968,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"real-world":[1],"events":[2],"from":[3,36],"live":[4,173],"market":[5,89,174],"signals":[6],"demands":[7],"systems":[8],"that":[9,38],"fuse":[10],"qualitative":[11],"news":[12,65],"with":[13,54],"quantitative":[14],"order-book":[15,118],"dynamics":[16],"under":[17,86,172],"strict":[18],"temporal":[19],"discipline":[20],"--":[21,76,82,137,147],"a":[22,32,55,63,124,180],"challenge":[23],"existing":[24],"benchmarks":[25],"fail":[26],"to":[27],"capture.":[28],"We":[29],"present":[30],"\\textbf{PolyBench},":[31],"multimodal":[33],"benchmark":[34],"derived":[35],"Polymarket":[37],"records":[39],"point-in-time":[40],"cross-sections":[41],"of":[42,130],"38,666":[43],"binary":[44],"prediction":[45],"markets":[46],"spanning":[47,77],"4,997":[48],"events,":[49],"synchronously":[50],"coupling":[51],"each":[52],"snapshot":[53],"Central":[56],"Limit":[57],"Order":[58],"Book":[59],"(CLOB)":[60],"state":[61],"and":[62,79,95,113,142,168,176,191],"real-time":[64],"stream.":[66],"Using":[67],"PolyBench,":[68],"we":[69],"evaluate":[70],"seven":[71,131],"state-of-the-art":[72],"Large":[73],"Language":[74],"Models":[75],"open-":[78],"closed-source":[80],"families":[81],"generating":[83],"36,165":[84],"predictions":[85],"identical,":[87],"timestamp-locked":[88],"states":[90],"collected":[91],"between":[92,164],"February":[93],"6":[94],"12,":[96],"2026.":[97],"Our":[98,189],"multidimensional":[99],"framework":[100],"assesses":[101],"directional":[102],"accuracy,":[103],"our":[104],"proposed":[105],"Confidence-Weighted":[106],"Return":[107],"(CWR),":[108],"Annualized":[109],"Percentage":[110],"Yield":[111],"(APY),":[112],"Sharpe":[114],"ratio":[115],"via":[116],"realistic":[117],"execution":[119],"simulation.":[120],"The":[121],"results":[122],"reveal":[123],"pronounced":[125],"performance":[126],"divergence:":[127],"only":[128],"two":[129],"models":[132],"achieve":[133],"positive":[134],"financial":[135],"returns":[136],"MiMo-V2-Flash":[138],"at":[139,144,194],"\\textbf{17.6%}":[140],"CWR":[141,146],"Gemini-3-Flash":[143],"6.2%":[145],"while":[148],"the":[149,162],"remaining":[150],"five":[151],"incur":[152],"losses":[153],"despite":[154],"uniformly":[155],"high":[156],"stated":[157],"confidence.":[158],"These":[159],"findings":[160],"highlight":[161],"gap":[163],"surface-level":[165],"language":[166],"fluency":[167],"genuine":[169],"probabilistic":[170],"reasoning":[171],"uncertainty,":[175],"establish":[177],"PolyBench":[178],"as":[179],"contamination-proof,":[181],"financially-grounded":[182],"evaluation":[183],"standard":[184],"for":[185],"future":[186],"LLM":[187],"research.":[188],"dataset":[190],"code":[192],"available":[193],"\\underline{\\href{https://github.com/PolyBench/PolyBench}{https://github.com/PolyBench/PolyBench}}.":[195]},"counts_by_year":[],"updated_date":"2026-04-18T06:05:20.339008","created_date":"2026-04-18T00:00:00"}