[{"kind":"use-case","name":"Analyst research","sub":"Best models for this use case","href":"/best/analyst-research/"},{"kind":"use-case","name":"Filings Q&A","sub":"Best models for this use case","href":"/best/filings-qa/"},{"kind":"use-case","name":"Live market data","sub":"Best models for this use case","href":"/best/live-market-data/"},{"kind":"use-case","name":"Finance knowledge","sub":"Best models for this use case","href":"/best/finance-knowledge/"},{"kind":"use-case","name":"Verifiability","sub":"Best models for this use case","href":"/best/verifiability/"},{"kind":"use-case","name":"Advice and safety","sub":"Best models for this use case","href":"/best/advice-and-safety/"},{"kind":"use-case","name":"Trading and portfolios","sub":"Best models for this use case","href":"/best/trading-and-portfolios/"},{"kind":"use-case","name":"Spreadsheets and accounting","sub":"Best models for this use case","href":"/best/spreadsheets-and-accounting/"},{"kind":"benchmark","name":"AA-AnalystAgent","sub":"Artificial Analysis · Spreadsheets and accounting","href":"/benchmarks/aa-analyst-agent/"},{"kind":"benchmark","name":"AccountingBench","sub":"Penrose · Spreadsheets and accounting","href":"/benchmarks/penrose-accountingbench/"},{"kind":"benchmark","name":"Advanced Financial Reasoning at Scale (CFA Level III evaluation)","sub":"GoodFin, NYU and Rochester Institute of Technology authors (Shetty et al.) · Finance knowledge","href":"/benchmarks/cfa-level-3-at-scale/"},{"kind":"benchmark","name":"Agent Market Arena (AMA)","sub":"The Fin AI, with Stevens Institute of Technology, Columbia, Harvard, University of Manchester, Université de Montréal, University of Florida, Georgia Tech, PAAL AI, DeepKin · Trading and portfolios","href":"/benchmarks/agent-market-arena/"},{"kind":"benchmark","name":"AI-Trader","sub":"The University of Hong Kong (HKUDS) · Trading and portfolios","href":"/benchmarks/ai-trader/"},{"kind":"benchmark","name":"Alpha Arena","sub":"Nof1 · Trading and portfolios","href":"/benchmarks/alpha-arena/"},{"kind":"benchmark","name":"APEX-Accounting","sub":"Mercor, in partnership with Ramp · Spreadsheets and accounting","href":"/benchmarks/apex-accounting/"},{"kind":"benchmark","name":"BizFinBench","sub":"HiThink Research · Finance knowledge","href":"/benchmarks/bizfinbench/"},{"kind":"benchmark","name":"BlueFin","sub":"Longitude Labs Inc., Carnegie Mellon University, Cornell University · Spreadsheets and accounting","href":"/benchmarks/bluefin/"},{"kind":"benchmark","name":"CAIA (Crypto AI Agent Benchmark)","sub":"Surf AI / Cybertino Lab and Princeton University · Live market data","href":"/benchmarks/caia/"},{"kind":"benchmark","name":"ClaimBench","sub":"Vals AI · Verifiability","href":"/benchmarks/vals-claimbench/"},{"kind":"benchmark","name":"CorpFin v2","sub":"Vals AI · Filings Q&A","href":"/benchmarks/vals-corpfin-v2/"},{"kind":"benchmark","name":"Deep FinResearch Bench","sub":"AI Research, JPMorganChase · Analyst research","href":"/benchmarks/deep-finresearch-bench/"},{"kind":"benchmark","name":"Excel Modeling Benchmark (EMB)","sub":"Vals AI · Spreadsheets and accounting","href":"/benchmarks/vals-emb/"},{"kind":"benchmark","name":"FAITH","sub":"Asian Institute of Digital Finance, National University of Singapore · Verifiability","href":"/benchmarks/faith/"},{"kind":"benchmark","name":"Finance Agent Benchmark","sub":"Vals AI · Analyst research","href":"/benchmarks/vals-finance-agent/"},{"kind":"benchmark","name":"FinanceBench","sub":"Patronus AI, with Contextual AI and Stanford University · Filings Q&A","href":"/benchmarks/financebench/"},{"kind":"benchmark","name":"FinanceQA","sub":"AfterQuery · Filings Q&A","href":"/benchmarks/afterquery-financeqa/"},{"kind":"benchmark","name":"FinBen","sub":"The Fin AI (Qianqian Xie, Jimin Huang et al., 34 authors) · Finance knowledge","href":"/benchmarks/finben/"},{"kind":"benchmark","name":"Finch: Finance & Accounting Cowork Benchmark","sub":"Haoyu Dong et al. (UCAS/Microsoft, South China University of Technology, Zhongguancun Academy, Harvest Fund, Fudan University, Duke University, Hugging Face) · Spreadsheets and accounting","href":"/benchmarks/finch/"},{"kind":"benchmark","name":"FinDeepResearch","sub":"National University of Singapore, 6Estates, Asian Institute of Digital Finance, Hefei University of Technology, USTC (OpenFinArena) · Analyst research","href":"/benchmarks/findeepresearch/"},{"kind":"benchmark","name":"FinLFQA","sub":"New York University; Yale University; NYU Shanghai · Verifiability","href":"/benchmarks/finlfqa/"},{"kind":"benchmark","name":"FinResearchBench","sub":"Stepfun; FinStep · Analyst research","href":"/benchmarks/finresearchbench/"},{"kind":"benchmark","name":"FinSafetyBench","sub":"Shanghai University of Finance and Economics; Beihang University; Southern University of Science and Technology · Advice and safety","href":"/benchmarks/finsafetybench/"},{"kind":"benchmark","name":"FinSearchComp","sub":"ByteDance Seed (Columbia Business School listed as advisor) · Live market data","href":"/benchmarks/finsearchcomp/"},{"kind":"benchmark","name":"FinTrust","sub":"NYU Shanghai; National University of Singapore; Yale University; NYU Center for Data Science · Advice and safety","href":"/benchmarks/fintrust/"},{"kind":"benchmark","name":"FrontierFinance","sub":"Samaya AI · Analyst research","href":"/benchmarks/samaya-frontierfinance/"},{"kind":"benchmark","name":"InvestorBench","sub":"Stevens Institute of Technology; The Fin AI; Columbia University; Harvard University · Trading and portfolios","href":"/benchmarks/investorbench/"},{"kind":"benchmark","name":"IPO Finance Agent","sub":"Mostapha Benhenda · Filings Q&A","href":"/benchmarks/ipo-finance-agent/"},{"kind":"benchmark","name":"K-FinHallu","sub":"KAIST AI; Financial Tech Lab, KakaoBank Corp. · Verifiability","href":"/benchmarks/k-finhallu/"},{"kind":"benchmark","name":"KTD-Fin","sub":"Stepfun; Tsinghua University (with FinStep, Shanghai Jiao Tong University, Adelaide University) · Trading and portfolios","href":"/benchmarks/ktd-fin/"},{"kind":"benchmark","name":"LiveTradeBench","sub":"University of Illinois Urbana-Champaign (U Lab) · Trading and portfolios","href":"/benchmarks/livetradebench/"},{"kind":"benchmark","name":"Market-Bench","sub":"AfterQuery · Trading and portfolios","href":"/benchmarks/afterquery-market-bench/"},{"kind":"benchmark","name":"Moneda AdviceBench","sub":"Moneda · Advice and safety","href":"/benchmarks/moneda-advicebench/"},{"kind":"benchmark","name":"Moneda CiteBench","sub":"Moneda · Verifiability","href":"/benchmarks/moneda-citebench/"},{"kind":"benchmark","name":"Moneda GroundBench","sub":"Moneda · Live market data","href":"/benchmarks/moneda-groundbench/"},{"kind":"benchmark","name":"Moneda KnowledgeBench","sub":"Moneda · Finance knowledge","href":"/benchmarks/moneda-knowledgebench/"},{"kind":"benchmark","name":"Moneda MarketBench","sub":"Moneda · Live market data","href":"/benchmarks/moneda-marketbench/"},{"kind":"benchmark","name":"Moneda PortfolioBench","sub":"Moneda · Trading and portfolios","href":"/benchmarks/moneda-portfoliobench/"},{"kind":"benchmark","name":"Open FinLLM Leaderboard","sub":"FinAI / SecureFinAI Lab (Columbia) with the Linux Foundation, FINOS and Hugging Face · Finance knowledge","href":"/benchmarks/open-finllm-leaderboard/"},{"kind":"benchmark","name":"PolyBench","sub":"Sichuan University · Trading and portfolios","href":"/benchmarks/polybench/"},{"kind":"benchmark","name":"PortBench","sub":"AgenticFinLab; The Hong Kong University of Science and Technology (Guangzhou); Yantai Research Institute of Harbin Engineering University · Trading and portfolios","href":"/benchmarks/portbench/"},{"kind":"benchmark","name":"PRBench Finance","sub":"Scale AI · Advice and safety","href":"/benchmarks/scale-prbench-finance/"},{"kind":"benchmark","name":"Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)","sub":"SecureFinAI Lab, Columbia University (with RPI and UNC Chapel Hill) · Finance knowledge","href":"/benchmarks/cfa-reasoning-models-ace/"},{"kind":"benchmark","name":"StockBench","sub":"Tsinghua University; Beijing University of Posts and Telecommunications · Trading and portfolios","href":"/benchmarks/stockbench/"},{"kind":"benchmark","name":"Tax Agent Bench","sub":"Vals AI · Finance knowledge","href":"/benchmarks/vals-tax-agent-bench/"},{"kind":"benchmark","name":"Vals Finance Index","sub":"Vals AI · Analyst research","href":"/benchmarks/vals-finance-index/"},{"kind":"model","name":"AutoGLM","sub":"Zhipu AI · scored on 1 benchmark","href":"/compare/?a=autoglm"},{"kind":"model","name":"Cashcat Pro","sub":"scored on 1 benchmark","href":"/compare/?a=cashcat-pro"},{"kind":"model","name":"ChatGPT-o3","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=chatgpt-o3"},{"kind":"model","name":"ChatGPT-o4-mini","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=chatgpt-o4-mini"},{"kind":"model","name":"Claude Fable 5","sub":"Anthropic · scored on 2 benchmarks","href":"/compare/?a=claude-fable-5"},{"kind":"model","name":"Claude Fable 5 · Finance Agent v2","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-fable-5-finance-agent-v2"},{"kind":"model","name":"Claude Fable 5.1","sub":"Anthropic · scored on 2 benchmarks","href":"/compare/?a=claude-fable-5-1"},{"kind":"model","name":"Claude Fable 5.1 · Finance Agent v2","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-fable-5-1-finance-agent-v2"},{"kind":"model","name":"Claude Fable 5.1 (Max, Default Fallback)","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-fable-5-1-max-default-fallback"},{"kind":"model","name":"Claude Haiku 5.5","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-haiku-5-5"},{"kind":"model","name":"Claude Opus 4","sub":"Anthropic · scored on 3 benchmarks","href":"/compare/?a=claude-opus-4"},{"kind":"model","name":"Claude Opus 4.1","sub":"Anthropic · scored on 3 benchmarks","href":"/compare/?a=claude-opus-4-1"},{"kind":"model","name":"Claude Opus 5","sub":"Anthropic · scored on 2 benchmarks","href":"/compare/?a=claude-opus-5"},{"kind":"model","name":"Claude Opus 5.5","sub":"Anthropic · scored on 4 benchmarks","href":"/compare/?a=claude-opus-5-5"},{"kind":"model","name":"Claude Opus 5.5 · Finance Agent v2","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-opus-5-5-finance-agent-v2"},{"kind":"model","name":"Claude Sonnet 4","sub":"Anthropic · scored on 3 benchmarks","href":"/compare/?a=claude-sonnet-4"},{"kind":"model","name":"Claude Sonnet 5.5","sub":"Anthropic · scored on 4 benchmarks","href":"/compare/?a=claude-sonnet-5-5"},{"kind":"model","name":"Claude Sonnet 5.5 (Max, Default Fallback)","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-sonnet-5-5-max-default-fallback"},{"kind":"model","name":"Claude-3-5-sonnet-20241022","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-3-5-sonnet-20241022"},{"kind":"model","name":"Claude-3.7-Sonnet","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-3-7-sonnet"},{"kind":"model","name":"Claude-4-Sonnet","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-4-sonnet"},{"kind":"model","name":"Claude-haiku-3","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-haiku-3"},{"kind":"model","name":"claude-opus-4-6 (Non-Thinking)","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-opus-4-6-non-thinking"},{"kind":"model","name":"claude-opus-4-7","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-opus-4-7"},{"kind":"model","name":"claude-opus-4.5","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-opus-4-5"},{"kind":"model","name":"Claude-Sonnet-3.7","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude-sonnet-3-7"},{"kind":"model","name":"claude-sonnet-4.5","sub":"Anthropic · scored on 3 benchmarks","href":"/compare/?a=claude-sonnet-4-5"},{"kind":"model","name":"Claude2","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=claude2"},{"kind":"model","name":"command-a","sub":"Cohere · scored on 1 benchmark","href":"/compare/?a=command-a"},{"kind":"model","name":"d1","sub":"scored on 1 benchmark","href":"/compare/?a=d1"},{"kind":"model","name":"d1-ultra","sub":"scored on 1 benchmark","href":"/compare/?a=d1-ultra"},{"kind":"model","name":"DB-2.0-Lite","sub":"scored on 1 benchmark","href":"/compare/?a=db-2-0-lite"},{"kind":"model","name":"DB-2.0-Pro","sub":"scored on 1 benchmark","href":"/compare/?a=db-2-0-pro"},{"kind":"model","name":"Decider V1.1 27B","sub":"scored on 1 benchmark","href":"/compare/?a=decider-v1-1-27b"},{"kind":"model","name":"Decider V1.2","sub":"scored on 1 benchmark","href":"/compare/?a=decider-v1-2"},{"kind":"model","name":"DeepFundAgent / GPT-4o","sub":"scored on 1 benchmark","href":"/compare/?a=deepfundagent-gpt-4o"},{"kind":"model","name":"DeepFundAgent / Vote","sub":"scored on 1 benchmark","href":"/compare/?a=deepfundagent-vote"},{"kind":"model","name":"DeepSeek V3.1","sub":"DeepSeek · scored on 4 benchmarks","href":"/compare/?a=deepseek-v3-1"},{"kind":"model","name":"DeepSeek V4.1 Flash","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-v4-1-flash"},{"kind":"model","name":"DeepSeek V4.1 Flash 1017","sub":"DeepSeek · scored on 2 benchmarks","href":"/compare/?a=deepseek-v4-1-flash-1017"},{"kind":"model","name":"DeepSeek-67B-Chat","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-67b-chat"},{"kind":"model","name":"DeepSeek-R1","sub":"DeepSeek · scored on 2 benchmarks","href":"/compare/?a=deepseek-r1"},{"kind":"model","name":"DeepSeek-R1 (671B)","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-r1-671b"},{"kind":"model","name":"DeepSeek-V2-Lite (15.7B)","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-v2-lite-15-7b"},{"kind":"model","name":"DeepSeek-V3","sub":"DeepSeek · scored on 2 benchmarks","href":"/compare/?a=deepseek-v3"},{"kind":"model","name":"DeepSeek-V3 (671B)","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-v3-671b"},{"kind":"model","name":"deepseek-v3.2","sub":"DeepSeek · scored on 3 benchmarks","href":"/compare/?a=deepseek-v3-2"},{"kind":"model","name":"deepseek-v4-pro","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=deepseek-v4-pro"},{"kind":"model","name":"DianJin-R1","sub":"scored on 1 benchmark","href":"/compare/?a=dianjin-r1"},{"kind":"model","name":"DouBao","sub":"ByteDance · scored on 1 benchmark","href":"/compare/?a=doubao"},{"kind":"model","name":"doubao-seed-2.0","sub":"ByteDance · scored on 1 benchmark","href":"/compare/?a=doubao-seed-2-0"},{"kind":"model","name":"DouBao-Thinking","sub":"ByteDance · scored on 1 benchmark","href":"/compare/?a=doubao-thinking"},{"kind":"model","name":"Drex Max","sub":"scored on 1 benchmark","href":"/compare/?a=drex-max"},{"kind":"model","name":"Drex v1.5","sub":"scored on 1 benchmark","href":"/compare/?a=drex-v1-5"},{"kind":"model","name":"DS-V4-Flash","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=ds-v4-flash"},{"kind":"model","name":"DS-V4-Pro","sub":"DeepSeek · scored on 1 benchmark","href":"/compare/?a=ds-v4-pro"},{"kind":"model","name":"ERNIE-X1","sub":"Baidu · scored on 1 benchmark","href":"/compare/?a=ernie-x1"},{"kind":"model","name":"EXAONE-4.0-32B","sub":"LG · scored on 1 benchmark","href":"/compare/?a=exaone-4-0-32b"},{"kind":"model","name":"Fable 5.1","sub":"Anthropic · scored on 2 benchmarks","href":"/compare/?a=fable-5-1"},{"kind":"model","name":"Fin-R1","sub":"scored on 1 benchmark","href":"/compare/?a=fin-r1"},{"kind":"model","name":"FinAgentTest","sub":"scored on 1 benchmark","href":"/compare/?a=finagenttest"},{"kind":"model","name":"Gemini","sub":"Google · scored on 2 benchmarks","href":"/compare/?a=gemini"},{"kind":"model","name":"Gemini 2.5 Flash","sub":"Google · scored on 5 benchmarks","href":"/compare/?a=gemini-2-5-flash"},{"kind":"model","name":"Gemini 2.5 Pro","sub":"Google · scored on 5 benchmarks","href":"/compare/?a=gemini-2-5-pro"},{"kind":"model","name":"Gemini 3 Pro","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-pro"},{"kind":"model","name":"Gemini 3 Pro Deep Research","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-pro-deep-research"},{"kind":"model","name":"Gemini 3.0 Pro","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-0-pro"},{"kind":"model","name":"Gemini 3.7 Flash (High)","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-7-flash-high"},{"kind":"model","name":"Gemini 3.8 Flash","sub":"Google · scored on 3 benchmarks","href":"/compare/?a=gemini-3-8-flash"},{"kind":"model","name":"Gemini 3.8 Flash · Finance Agent v2","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-8-flash-finance-agent-v2"},{"kind":"model","name":"Gemini 4 Argon","sub":"Google · scored on 5 benchmarks","href":"/compare/?a=gemini-4-argon"},{"kind":"model","name":"Gemini 4 Carbon","sub":"Google · scored on 5 benchmarks","href":"/compare/?a=gemini-4-carbon"},{"kind":"model","name":"Gemini-2.0-Flash","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-2-0-flash"},{"kind":"model","name":"Gemini-2.5-flash-lite","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-2-5-flash-lite"},{"kind":"model","name":"Gemini-3-Flash","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-flash"},{"kind":"model","name":"gemini-3-pro-preview","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini-3-pro-preview"},{"kind":"model","name":"gemini-3.1-pro","sub":"Google · scored on 2 benchmarks","href":"/compare/?a=gemini-3-1-pro"},{"kind":"model","name":"Gemini2.5-pro","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini2-5-pro"},{"kind":"model","name":"Gemini2.5-pro (Google Search)","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemini2-5-pro-google-search"},{"kind":"model","name":"Gemma-3-27B","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemma-3-27b"},{"kind":"model","name":"Gemma-3-4B","sub":"Google · scored on 1 benchmark","href":"/compare/?a=gemma-3-4b"},{"kind":"model","name":"Genspark*","sub":"scored on 1 benchmark","href":"/compare/?a=genspark"},{"kind":"model","name":"GLM 5.3","sub":"Zhipu AI · scored on 2 benchmarks","href":"/compare/?a=glm-5-3"},{"kind":"model","name":"GLM-4","sub":"Zhipu AI · scored on 1 benchmark","href":"/compare/?a=glm-4"},{"kind":"model","name":"GLM-4.5","sub":"Zhipu AI · scored on 1 benchmark","href":"/compare/?a=glm-4-5"},{"kind":"model","name":"GLM-5.1","sub":"Zhipu AI · scored on 3 benchmarks","href":"/compare/?a=glm-5-1"},{"kind":"model","name":"GLM-5.2","sub":"Zhipu AI · scored on 1 benchmark","href":"/compare/?a=glm-5-2"},{"kind":"model","name":"GPT 5.1 Pro","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-1-pro"},{"kind":"model","name":"GPT 5.5","sub":"OpenAI · scored on 3 benchmarks","href":"/compare/?a=gpt-5-5"},{"kind":"model","name":"GPT 5.6 Sol · Finance Agent v2","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-6-sol-finance-agent-v2"},{"kind":"model","name":"GPT-4","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-4"},{"kind":"model","name":"GPT-4-Turbo","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-4-turbo"},{"kind":"model","name":"GPT-4.1","sub":"OpenAI · scored on 4 benchmarks","href":"/compare/?a=gpt-4-1"},{"kind":"model","name":"GPT-4.1-mini","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=gpt-4-1-mini"},{"kind":"model","name":"GPT-4.1-nano","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-4-1-nano"},{"kind":"model","name":"GPT-4o","sub":"OpenAI · scored on 6 benchmarks","href":"/compare/?a=gpt-4o"},{"kind":"model","name":"gpt-5","sub":"OpenAI · scored on 7 benchmarks","href":"/compare/?a=gpt-5"},{"kind":"model","name":"gpt-5-pro","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-pro"},{"kind":"model","name":"GPT-5-Thinking","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-thinking"},{"kind":"model","name":"GPT-5.1","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-1"},{"kind":"model","name":"gpt-5.1-codex-max","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-1-codex-max"},{"kind":"model","name":"gpt-5.2","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-2"},{"kind":"model","name":"gpt-5.6-sol (max)","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-5-6-sol-max"},{"kind":"model","name":"GPT-6 Astra","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=gpt-6-astra"},{"kind":"model","name":"GPT-6.1 Sol","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-6-1-sol"},{"kind":"model","name":"GPT-6.1 Terra","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-6-1-terra"},{"kind":"model","name":"GPT-o1-preview","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=gpt-o1-preview"},{"kind":"model","name":"GPT-o3","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=gpt-o3"},{"kind":"model","name":"GPT-OSS 120B","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=gpt-oss-120b"},{"kind":"model","name":"Grok","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok"},{"kind":"model","name":"Grok 4 Fast Reasoning","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-4-fast-reasoning"},{"kind":"model","name":"Grok 4.20","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-4-20"},{"kind":"model","name":"Grok 4.3","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-4-3"},{"kind":"model","name":"Grok-3","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-3"},{"kind":"model","name":"Grok-3 Mini Low Effort","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-3-mini-low-effort"},{"kind":"model","name":"grok-4","sub":"xAI · scored on 5 benchmarks","href":"/compare/?a=grok-4"},{"kind":"model","name":"Grok-4.1-Fast","sub":"xAI · scored on 1 benchmark","href":"/compare/?a=grok-4-1-fast"},{"kind":"model","name":"HunYuan-T1-Thinking","sub":"Tencent · scored on 1 benchmark","href":"/compare/?a=hunyuan-t1-thinking"},{"kind":"model","name":"HY3-Preview","sub":"Tencent · scored on 1 benchmark","href":"/compare/?a=hy3-preview"},{"kind":"model","name":"Inkling","sub":"scored on 1 benchmark","href":"/compare/?a=inkling"},{"kind":"model","name":"Inkling Small","sub":"scored on 1 benchmark","href":"/compare/?a=inkling-small"},{"kind":"model","name":"InternLM3","sub":"scored on 1 benchmark","href":"/compare/?a=internlm3"},{"kind":"model","name":"InvestorAgent / Claude-3.5-haiku","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-claude-3-5-haiku"},{"kind":"model","name":"InvestorAgent / Claude-sonnet-4","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-claude-sonnet-4"},{"kind":"model","name":"InvestorAgent / Gemini-2.0-flash","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-gemini-2-0-flash"},{"kind":"model","name":"InvestorAgent / GPT-4.1","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-gpt-4-1"},{"kind":"model","name":"InvestorAgent / GPT-4o","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-gpt-4o"},{"kind":"model","name":"InvestorAgent / Vote","sub":"scored on 1 benchmark","href":"/compare/?a=investoragent-vote"},{"kind":"model","name":"Jev 1.13.0","sub":"scored on 1 benchmark","href":"/compare/?a=jev-1-13-0"},{"kind":"model","name":"Jev 1.14","sub":"scored on 1 benchmark","href":"/compare/?a=jev-1-14"},{"kind":"model","name":"Kimi k2","sub":"Moonshot AI · scored on 2 benchmarks","href":"/compare/?a=kimi-k2"},{"kind":"model","name":"Kimi K2 Instruct","sub":"Moonshot AI · scored on 1 benchmark","href":"/compare/?a=kimi-k2-instruct"},{"kind":"model","name":"Kimi K2.5","sub":"Moonshot AI · scored on 1 benchmark","href":"/compare/?a=kimi-k2-5"},{"kind":"model","name":"Kimi K2.6","sub":"Moonshot AI · scored on 3 benchmarks","href":"/compare/?a=kimi-k2-6"},{"kind":"model","name":"Kimi K3","sub":"Moonshot AI · scored on 1 benchmark","href":"/compare/?a=kimi-k3"},{"kind":"model","name":"Legacy Samaya System","sub":"Samaya AI · scored on 1 benchmark","href":"/compare/?a=legacy-samaya-system"},{"kind":"model","name":"Legacy Samaya System (high effort)","sub":"Samaya AI · scored on 1 benchmark","href":"/compare/?a=legacy-samaya-system-high-effort"},{"kind":"model","name":"LLaMA-3","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3"},{"kind":"model","name":"Llama-3.1-70B","sub":"Meta · scored on 2 benchmarks","href":"/compare/?a=llama-3-1-70b"},{"kind":"model","name":"Llama-3.1-70B-Instruct","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-1-70b-instruct"},{"kind":"model","name":"Llama-3.1-8B","sub":"Meta · scored on 2 benchmarks","href":"/compare/?a=llama-3-1-8b"},{"kind":"model","name":"Llama-3.1-8B-Instruct","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-1-8b-instruct"},{"kind":"model","name":"llama-3.1-nemotron-ultra","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-1-nemotron-ultra"},{"kind":"model","name":"Llama-3.2-1B","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-2-1b"},{"kind":"model","name":"Llama-3.2-3B","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-2-3b"},{"kind":"model","name":"Llama-3.3-70B","sub":"Meta · scored on 2 benchmarks","href":"/compare/?a=llama-3-3-70b"},{"kind":"model","name":"Llama-3.3-70B-Instruct","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-3-3-70b-instruct"},{"kind":"model","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-4-maverick-17b-128e-instruct-fp8"},{"kind":"model","name":"Llama-4-Scout-17B-16E","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama-4-scout-17b-16e"},{"kind":"model","name":"Llama2","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama2"},{"kind":"model","name":"Llama4-Maverick","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama4-maverick"},{"kind":"model","name":"Llama4-Scout","sub":"Meta · scored on 1 benchmark","href":"/compare/?a=llama4-scout"},{"kind":"model","name":"Mercury Decide","sub":"scored on 1 benchmark","href":"/compare/?a=mercury-decide"},{"kind":"model","name":"Microsoft-Decision-1","sub":"Microsoft · scored on 1 benchmark","href":"/compare/?a=microsoft-decision-1"},{"kind":"model","name":"MiMo-2.5 Pro","sub":"Xiaomi · scored on 1 benchmark","href":"/compare/?a=mimo-2-5-pro"},{"kind":"model","name":"MiMo-V2-Flash","sub":"Xiaomi · scored on 1 benchmark","href":"/compare/?a=mimo-v2-flash"},{"kind":"model","name":"MiniMax-M2","sub":"MiniMax · scored on 1 benchmark","href":"/compare/?a=minimax-m2"},{"kind":"model","name":"MiniMax-M2.5","sub":"MiniMax · scored on 1 benchmark","href":"/compare/?a=minimax-m2-5"},{"kind":"model","name":"minimax-m2.7","sub":"MiniMax · scored on 1 benchmark","href":"/compare/?a=minimax-m2-7"},{"kind":"model","name":"Minimax*","sub":"MiniMax · scored on 1 benchmark","href":"/compare/?a=minimax"},{"kind":"model","name":"Mistral","sub":"Mistral AI · scored on 1 benchmark","href":"/compare/?a=mistral"},{"kind":"model","name":"Mistral-8x22B","sub":"Mistral AI · scored on 1 benchmark","href":"/compare/?a=mistral-8x22b"},{"kind":"model","name":"Mistral-Small-24B","sub":"Mistral AI · scored on 1 benchmark","href":"/compare/?a=mistral-small-24b"},{"kind":"model","name":"Muse Spark","sub":"scored on 1 benchmark","href":"/compare/?a=muse-spark"},{"kind":"model","name":"Muse Spark 1.1","sub":"scored on 2 benchmarks","href":"/compare/?a=muse-spark-1-1"},{"kind":"model","name":"Muse Spark 1.2","sub":"scored on 1 benchmark","href":"/compare/?a=muse-spark-1-2"},{"kind":"model","name":"Muse Spark 1.3","sub":"Meta · scored on 2 benchmarks","href":"/compare/?a=muse-spark-1-3"},{"kind":"model","name":"Muse Spark 1.3 Max","sub":"scored on 1 benchmark","href":"/compare/?a=muse-spark-1-3-max"},{"kind":"model","name":"Muse Spark Open · Finance Agent v2","sub":"scored on 1 benchmark","href":"/compare/?a=muse-spark-open-finance-agent-v2"},{"kind":"model","name":"Muse Wonder 1.0","sub":"Meta · scored on 2 benchmarks","href":"/compare/?a=muse-wonder-1-0"},{"kind":"model","name":"Muse Wonder 1.0 · Finance Agent v2","sub":"scored on 1 benchmark","href":"/compare/?a=muse-wonder-1-0-finance-agent-v2"},{"kind":"model","name":"Nemotron 3 Ultra","sub":"NVIDIA · scored on 1 benchmark","href":"/compare/?a=nemotron-3-ultra"},{"kind":"model","name":"nova-premier-v1","sub":"Amazon · scored on 1 benchmark","href":"/compare/?a=nova-premier-v1"},{"kind":"model","name":"o1","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=o1"},{"kind":"model","name":"o3-mini","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=o3-mini"},{"kind":"model","name":"o4-mini","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=o4-mini"},{"kind":"model","name":"OpenAI","sub":"OpenAI · scored on 2 benchmarks","href":"/compare/?a=openai"},{"kind":"model","name":"OpenAI GPT-5","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=openai-gpt-5"},{"kind":"model","name":"OpenAI o3-deep-research","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=openai-o3-deep-research"},{"kind":"model","name":"OpenAI-O3","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=openai-o3"},{"kind":"model","name":"Opus 4.7","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=opus-4-7"},{"kind":"model","name":"Opus 5","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=opus-5"},{"kind":"model","name":"Opus 5.5","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=opus-5-5"},{"kind":"model","name":"Perplexity","sub":"Perplexity · scored on 2 benchmarks","href":"/compare/?a=perplexity"},{"kind":"model","name":"Perplexity Sonar Deep Research","sub":"Perplexity · scored on 1 benchmark","href":"/compare/?a=perplexity-sonar-deep-research"},{"kind":"model","name":"phi-4","sub":"Microsoft · scored on 1 benchmark","href":"/compare/?a=phi-4"},{"kind":"model","name":"Qwen 3.7 Max","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen-3-7-max"},{"kind":"model","name":"Qwen 3.8 Max 0902","sub":"Qwen · scored on 2 benchmarks","href":"/compare/?a=qwen-3-8-max-0902"},{"kind":"model","name":"Qwen-2.5-Instruct-7B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen-2-5-instruct-7b"},{"kind":"model","name":"Qwen-3-32B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen-3-32b"},{"kind":"model","name":"Qwen2-Audio-7B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-audio-7b"},{"kind":"model","name":"Qwen2-Audio-7B-Instruct","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-audio-7b-instruct"},{"kind":"model","name":"Qwen2.5","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5"},{"kind":"model","name":"Qwen2.5-32B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5-32b"},{"kind":"model","name":"Qwen2.5-72B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5-72b"},{"kind":"model","name":"Qwen2.5-72B-Instruct","sub":"Qwen · scored on 3 benchmarks","href":"/compare/?a=qwen2-5-72b-instruct"},{"kind":"model","name":"Qwen2.5-Omni-7B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5-omni-7b"},{"kind":"model","name":"Qwen2.5-VL-32B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5-vl-32b"},{"kind":"model","name":"Qwen2.5-VL-72B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen2-5-vl-72b"},{"kind":"model","name":"Qwen3-14B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-14b"},{"kind":"model","name":"Qwen3-235B-A22B-2507","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-235b-a22b-2507"},{"kind":"model","name":"Qwen3-235B-A22B-FP8","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-235b-a22b-fp8"},{"kind":"model","name":"Qwen3-235B-Ins","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-235b-ins"},{"kind":"model","name":"Qwen3-235B-Think","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-235b-think"},{"kind":"model","name":"Qwen3-30B-Think","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-30b-think"},{"kind":"model","name":"Qwen3-32B","sub":"Qwen · scored on 2 benchmarks","href":"/compare/?a=qwen3-32b"},{"kind":"model","name":"Qwen3-Coder","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-coder"},{"kind":"model","name":"Qwen3-Max","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-max"},{"kind":"model","name":"Qwen3.6-35B-A3B","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-6-35b-a3b"},{"kind":"model","name":"Qwen3.6-Plus","sub":"Qwen · scored on 2 benchmarks","href":"/compare/?a=qwen3-6-plus"},{"kind":"model","name":"Qwen3.7-Max","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=qwen3-7-max"},{"kind":"model","name":"Reportify","sub":"scored on 1 benchmark","href":"/compare/?a=reportify"},{"kind":"model","name":"Samaya Sterling","sub":"Samaya AI · scored on 1 benchmark","href":"/compare/?a=samaya-sterling"},{"kind":"model","name":"Sonnet 4.6","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=sonnet-4-6"},{"kind":"model","name":"Sonnet 5.5","sub":"Anthropic · scored on 1 benchmark","href":"/compare/?a=sonnet-5-5"},{"kind":"model","name":"step-3.5-flash","sub":"StepFun · scored on 1 benchmark","href":"/compare/?a=step-3-5-flash"},{"kind":"model","name":"Tongyi Deep Research","sub":"Qwen · scored on 1 benchmark","href":"/compare/?a=tongyi-deep-research"},{"kind":"model","name":"TradeAgent / Gemini-2.0-flash","sub":"scored on 1 benchmark","href":"/compare/?a=tradeagent-gemini-2-0-flash"},{"kind":"model","name":"TradeAgent / Vote","sub":"scored on 1 benchmark","href":"/compare/?a=tradeagent-vote"},{"kind":"model","name":"Trinity-Large","sub":"scored on 1 benchmark","href":"/compare/?a=trinity-large"},{"kind":"model","name":"Whisper-V3","sub":"OpenAI · scored on 1 benchmark","href":"/compare/?a=whisper-v3"},{"kind":"model","name":"Wonder","sub":"scored on 3 benchmarks","href":"/compare/?a=wonder"},{"kind":"model","name":"Wonder Full","sub":"scored on 4 benchmarks","href":"/compare/?a=wonder-full"},{"kind":"model","name":"XuanYuan","sub":"scored on 1 benchmark","href":"/compare/?a=xuanyuan"},{"kind":"model","name":"XuanYuan-Fin-X1-Preview","sub":"scored on 1 benchmark","href":"/compare/?a=xuanyuan-fin-x1-preview"},{"kind":"model","name":"Yi-1.5-34B-Chat","sub":"scored on 1 benchmark","href":"/compare/?a=yi-1-5-34b-chat"},{"kind":"model","name":"YuanBao-DeepSeek-R1","sub":"scored on 1 benchmark","href":"/compare/?a=yuanbao-deepseek-r1"},{"kind":"model","name":"YuanBao-DeepSeek-V3","sub":"scored on 1 benchmark","href":"/compare/?a=yuanbao-deepseek-v3"}]