Step 5 Preview overview
The Pareto frontier marks the best trade-offs between intelligence and cost. Progress begins when that boundary shifts outward.
Today, we’re introducing Step 5 Preview, our new flagship model for agentic work. It delivers frontier-level performance across software engineering and professional knowledge work, with particular strength in finance. Built on a sparse Mixture-of-Experts architecture, Step 5 Preview has 600B total parameters, with 27B active per token, and supports a 1M-token context window and vision input.
Across public and internal evaluations, Step 5 Preview performs strongly across software engineering, agentic tasks, professional knowledge work, and finance.
GDPval-AA v2 scores are based on the latest results from Artificial Analysis, as of Sep. 19, 2026.
Step 5 Preview scores 44 on the Artificial Analysis Intelligence Index. At a comparable level of intelligence, its task cost is substantially lower than similarly capable models.
We also evaluated Step 5 Preview on FrontierFinance, an external benchmark covering six investment use cases through 220 expert-crafted questions and 11,543 evaluation criteria. Its detailed scoring rubrics provide a complementary assessment of complex financial responses.
Step 5 Preview shows strong performance across information retrieval, valuation, and end-to-end financial research.
Benchmarking Step 5 Preview
The evaluations above highlight a subset of Step 5 Preview’s capabilities. The table below shows results across a broader set of reasoning, coding, agentic, financial, and multimodal benchmarks.
Selected benchmark results from StepFun announcement:
- Terminal-Bench v4: 33.3%
- SciCode: strong performance relative to peers
- GDPval-AA v2: competitive agentic real-world work scores
Try Step 5 Preview
Step 5 Preview is available today through our products and API. The model will be released with open weights on October 15.
Third-party benchmarking (Artificial Analysis)
Artificial Analysis independently benchmarked Step 5 Preview (released September 2026):
- Intelligence Index: 44 (#24 of 200 models)
- Speed: 99.8 output tokens per second
- Pricing: 2.70 per 1M output tokens, $0.71 cost per Intelligence Index task
- Context window: 1M tokens
- Input modality: text and image; output: text
- Reasoning model with extended thinking
- 600 billion total parameters, 27B active per token (sparse MoE)
- Available via StepFun API
Artificial Analysis notes Step 5 Preview is amongst the leading models in intelligence and well priced when comparing to other models of similar price, faster than average but very verbose (160M output tokens from Intelligence Index evaluation vs median 92M).