Step 5 Preview - Intelligence, Performance & Price Analysis | Artificial AnalysisArtificial AnalysisKArtificial AnalysisModelsCoding AgentsImage, Speech, VideoInferenceLeaderboardsAboutAI TrendsArenasKStepFun•Proprietary model•Released September 2026Step 5 Preview Intelligence, Performance & Price AnalysisCompareTry it out API Provider Benchmarks Model summaryIntelligenceUpdated#25 / 20044Artificial Analysis Intelligence Index4 out of 4 units for Intelligence.Speed#41 / 20099.8Output tokens per second3 out of 4 units for Speed.Cost#27 / 200In $1.00Out $2.70Cache Discount 95%$0.71Cost per Intelligence Index task2 out of 4 units for Cost.Verbosity#65 / 200160MOutput tokens from Intelligence Index4 out of 4 units for Verbosity.Comparison SummaryStep 5 Preview is amongst the leading models in intelligence and well priced when comparing to other models of similar price. It's also faster than average, however very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.Step 5 Preview scores 44 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 25). When evaluating the Intelligence Index, it generated 160M tokens, which is very verbose in comparison to the median of 90M.Pricing for Step 5 Preview is $1.00 per 1M input tokens (competitively priced, median: $1.88) and $2.70 per 1M output tokens (competitively priced, median: $10.00). In total, it cost $918.34 to evaluate Step 5 Preview on the Intelligence Index.At 100 tokens per second, Step 5 Preview is faster than average (65).Technical specificationsReasoningYesThis page shows the reasoning version of this model.A non-reasoning variant may also exist.Input modalitySupports: text and imageOutput modalitySupports: textContext window1M~1500 A4 pages of size 12 Arial font200 models in this classMetrics are compared against models of the same class:Non-reasoning models → compared only with other non-reasoning modelsReasoning models → compared across both reasoning and non-reasoningOpen weights models → compared only with other open weights models of the same size class:Tiny: ≤4B parametersSmall: 4B–40B parametersMedium: 40B–150B parametersLarge: >150B parametersProprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:<$0.15 per 1M tokens$0.15–$1 per 1M tokens>$1 per 1M tokensModel ComparisonAPI Provider BenchmarksHighlightsUpdatedIntelligenceArtificial Analysis Intelligence Index · Higher is betterSpeedOutput tokens per second · Higher is betterCost per TaskWeighted average cost (USD) per Intelligence Index task · Lower is betterIntelligenceUpdatedCapability IndexesBenchmarksIntelligence Index ComparisonsToken UseCostContext WindowSpeedLatencyEnd-to-End Response TimePrompt OptionsIntelligenceUpdatedArtificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.127 of 653 modelsAdd model from specific providerArtificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Open Weights / ProprietaryReasoning / Non-ReasoningText Only / Multimodal InputsArtificial Analysis Intelligence Index by Open Weights / ProprietaryArtificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.127 of 653 modelsAdd model from specific providerProprietaryOpen Weights (Commercial Use Restricted)Open WeightsArtificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Open WeightsIndicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.Capability IndexesMeasures the performance of models on specific capabilities and industriesFinance & AccountingStrategy & OpsLegalEngineeringEconomicsArtificial Analysis Finance & Accounting IndexIncorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better26 of 161 modelsAdd model from specific providerBenchmarksIntelligence EvaluationsIntelligence evaluations measured independently by Artificial Analysis · Higher is betterCodingAgenticTool UsePrivate DatasetUser InteractionFinanceMedicalLegalIntelligence IndexLong ContextMultimodalInstruction FollowingFaithfulnessWritingBusinessSee more18 of 26 evaluations27 of 653 modelsAdd model from specific providerAA-BriefcaseAgentic knowledge work, (Elo-500)/2000GDPval-AA v2Agentic real-world work tasks, (Elo-500)/2000AutomationBench-AAUpdatedAgentic SaaS workflowsTerminal-Bench 4.0NewAgentic coding & terminal useSciCodeCodingHumanity's Last ExamReasoning & knowledgeGDP.pdfNewProfessional document reasoning, All-passCritPtPhysics reasoningAA-Omniscience AccuracyKnowledgeAA-Omniscience Non-Hallucination Rate1 - hallucination rateAA-LCR v1.1Long context reasoningHarvey LAB-AALegal agentic work, criterion pass rateEnterpriseOps-Gym-AAAgentic business operationsAA-AnalystAgentQuantitative analysis on spreadsheets & documents𝜏³-BankingAgentic tool useITBench-AAKubernetes incident root-cause analysisMMMU-ProVisual reasoningMLCR-AANewMedical long context reasoningIntelligence Evaluation RelevanceWhile model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.Artificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.AA-BriefcaseAA-Briefcase EloAA-Briefcase Rubric Score (%)Analytical Quality & Presentation EloAA-Briefcase EloAA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better27 of 170 modelsAdd model from specific providerAA-Briefcase EloAA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.AA-OmniscienceAA-Omniscience IndexAA-Omniscience AccuracyAA-Omniscience Hallucination RateAA-Omniscience IndexAA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.27 of 528 modelsAdd model from specific providerAA-Omniscience IndexAA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.Intelligence Index ComparisonsIntelligence Index vs. Cost per TaskIntelligence Index vs. Time per TaskIntelligence Index vs. Output SpeedIntelligence Index vs. End-to-End Response TimeIntelligence Index vs. Cost per Intelligence Index TaskArtificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task27 of 653 modelsMost attractive quadrantPareto lineStepFunOpenAIAnthropicDeepSeekGoogleMetaSpaceXAIZ AIKimiAlibabaCost per Intelligence Index TaskWeighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.Artificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Token UseOutput Tokens per TaskIntelligence Index vs. Output Tokens per TaskIntelligence Index Token UseIntelligence Index vs. Token UseOutput Tokens per Intelligence Index TaskWeighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index27 of 653 modelsAnswerReasoningOutput Tokens per Intelligence Index TaskThe number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).CostCost per TaskIntelligence Index vs. Cost per TaskEvaluation BreakdownCost per Intelligence Index TaskWeighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better27 of 653 modelsAnswerReasoningCache WriteCache HitInputCost per Intelligence Index TaskWeighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.Intelligence Index Total CostIntelligence Index vs. Total CostCost to Run Artificial Analysis Intelligence IndexCost (USD) to run all evaluations in the Artificial Analysis Intelligence Index27 of 653 modelsAdd model from specific providerOutputReasoningCache WriteCache ReadNon-Cache InputCost to Run Artificial Analysis Intelligence IndexThe cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).Cache Hit, Input, and Output PricingBlended PriceBlended Price (Stacked)Cache DiscountIntelligence Index vs. PriceIntelligence Index vs. Price (Log, Inverted)Image Input PricingPricing: Cache Hit, Input, and OutputPrice (USD per M Tokens)27 of 653 modelsAdd model from specific providerCache HitInputOutputCache HitPrice per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail. 4 more notesContext WindowContext WindowIntelligence Index vs. Context WindowContext WindowContext window: tokens limit · Higher is better27 of 653 modelsAdd model from specific providerContext Window for RAGLarger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.Context WindowMaximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).SpeedMeasured by Output Speed (tokens per second)Output SpeedOutput Speed by Prompt TypeOutput Speed VarianceOutput Speed Over TimeOutput Speed vs. PriceLatency vs. Output SpeedOutput SpeedOutput tokens per second · Higher is better27 of 653 modelsAdd model from specific providerOutput SpeedTokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).Model Performance RepresentationFigures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).Time per TaskIntelligence Index vs. Time per TaskCost vs. Time per TaskTime per Intelligence Index TaskWeighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better27 of 653 modelsTime per Intelligence Index TaskThe weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.LatencyMeasured by Time (seconds) to First TokenTime To First Answer TokenTime To First TokenLatency by Prompt TypeLatency VarianceLatency Over TimeLatency: Time To First Answer TokenSeconds to first answer token received · Accounts for reasoning model 'thinking' time27 of 653 modelsAdd model from specific providerThinking (reasoning models, when applicable)Input processingTime to First Answer TokenTime to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.End-to-End Response TimeSeconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speedEnd-to-End Response TimeEnd-to-End Response Time by Prompt TypeEnd-to-End Response Time Over TimeEnd-to-End Response TimeSeconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better27 of 653 modelsAdd model from specific providerOutputting time'Thinking' time (reasoning models)Input processing timeEnd-to-End Response TimeSeconds to receive a 500 token response. Key components:Input time: Time to receive the first response tokenThinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).Answer time: Time to generate 500 output tokens, based on output speedModel Performance RepresentationFigures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).Frequently Asked QuestionsCommon questions about Step 5 PreviewWhen was Step 5 Preview released?Step 5 Preview was released on September 18, 2026.Who created Step 5 Preview?Step 5 Preview was created by StepFun.How intelligent is Step 5 Preview?Step 5 Preview scores 44 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 25).How fast is Step 5 Preview?Step 5 Preview generates output at 99.8 tokens per second (based on StepFun's API), which is above average compared to other reasoning models in a similar price tier (median: 65.0 t/s).What is the latency of Step 5 Preview?Step 5 Preview has a time to first token (TTFT) of 2.96s (based on StepFun's API), which is better than average compared to other reasoning models in a similar price tier (median: 3.61s).How much does Step 5 Preview cost?Step 5 Preview costs $1.00 per 1M input tokens (very competitive, median: $1.88) and $2.70 per 1M output tokens (very competitive, median: $10.00), based on StepFun's API.What is Step 5 Preview API pricing?Step 5 Preview costs $1.00 per 1M input tokens and $2.70 per 1M output tokens (based on StepFun's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.51 per 1M tokens. Pricing may vary by provider. Compare provider pricingHow verbose is Step 5 Preview?When evaluated on the Intelligence Index, Step 5 Preview generated 160M output tokens, which is at the higher end compared to other reasoning models in a similar price tier (median: 90M).Is Step 5 Preview a reasoning model?Yes, Step 5 Preview is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.What input modalities does Step 5 Preview support?Step 5 Preview supports text and image input.What output modalities does Step 5 Preview support?Step 5 Preview supports text output.Can Step 5 Preview process images?Yes, Step 5 Preview supports image input and can analyze, describe, and answer questions about images.Is Step 5 Preview multimodal?Yes, Step 5 Preview is multimodal. It can process text and image input and generate text output.What is the context window of Step 5 Preview?Step 5 Preview has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.Is Step 5 Preview open source?No, Step 5 Preview is proprietary. The model weights are not publicly available.How many parameters does Step 5 Preview have?Step 5 Preview has 600 billion parameters.How does Step 5 Preview perform on benchmarks?Step 5 Preview achieves a score of 44 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.Is Step 5 Preview available via API?Yes, Step 5 Preview is available via API through 1 provider. Compare API providersWhere can I use Step 5 Preview?Step 5 Preview is available through 1 API provider. Compare providersArtificial AnalysisGet notified about new articlesEmail addressSubscribeArtificial AnalysisExploreLLM LeaderboardImage ArenaVideo ArenaAI AgentsEvaluationsProductsOptimaMicroEvalsModel RecommenderData PlaygroundImage LabCompanyAboutMethodologyContactArticlesXLinkedInYouTubeRednoteDiscord© 2026 Artificial AnalysisTerms of UseData Platform TermsPrivacy PolicyEnglish

Step 5 Preview is presented as a leading model in intelligence and pricing when contextualized against similar models, demonstrating a balanced performance profile across various benchmarks. The model was released in September 2026 and was created by StepFun. In terms of core capabilities, Step 5 Preview is multimodal, accepting both text and image input, and it generates text output. It supports an extensive context window of 1.0 million tokens, allowing it to process large amounts of information in a single request. Furthermore, the model is explicitly categorized as a reasoning model, indicating that it utilizes extended thinking or chain-of-thought reasoning to tackle complex problems before formulating its answers.

Performance evaluation via the Artificial Analysis Intelligence Index places Step 5 Preview at a score of 44, positioning it above the median of 25 among comparable models in a similar price tier. This intelligence assessment is derived from a comprehensive evaluation set that includes benchmarks such as AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, and AA-LCR v1.1. The model possesses 600 billion parameters.

Regarding operational speed, Step 5 Preview demonstrates high performance, generating output at 99.8 tokens per second, which is faster than the median speed of 65.0 tokens per second observed across other reasoning models in the comparable range. Latency metrics also indicate strong responsiveness, with a time to first token of 2.96 seconds, which outperforms the median of 3.61 seconds.

The economic analysis reveals competitive pricing. The model is priced at $1.00 per 1 million input tokens and $2.70 per 1 million output tokens. This pricing is competitive, especially when considering the median rates for input ($1.88) and output ($10.00) costs. When aggregating the total cost for running evaluations on the Intelligence Index, the total expenditure for Step 5 Preview was $918.34. The blended rate, considering potential cache hits and input/output ratios, suggests a highly competitive cost structure.

In analyzing verbosity, Step 5 Preview generated 160 million output tokens when evaluated on the Intelligence Index, which is on the higher end compared to the median of 90 million tokens for similar models, suggesting a trade-off where high intelligence might correlate with extended output. The model’s performance is further dissected through various capability indexes, including those for finance, accounting, strategy and operations, legal, engineering, and economics, as well as agentic work, coding, and factual reasoning, as reflected by the assessment of knowledge reliability and hallucination rates through the AA-Omniscience Index. The data shows that the model successfully integrates reasoning, factual knowledge, and task execution across diverse domains.