Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
Tested on 10 benchmarks · BenchGecko score 89.5. Top scores: Chatbot Arena Elo — Overall (1393.3%), OpenCompass — AIME2025 (95.7%), OpenCompass — IFEval (93.2%).
OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.
OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.
OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.
OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.
OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.
- Typetext
- Context262K tokens (~131 books)
- ReleasedJan 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Related Models
Claude Sonnet 5.5 · AnthropicGPT-5 Chat · OpenAIClaude Fable 5.1 · AnthropicQwen2.5 72B Instruct Abliterated · HuiHui AIClaude Opus 5 · AnthropicKey facts · as of 2026-10-05
- Step 3.5 Flash by stepfun. BenchGecko score 89.5, rank 6 of 312 scored models (normalized average of public benchmark scores).
- List price $0.10 input · $0.30 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): SiliconFlow (fp8) $0.10 in / $0.30 out.
How to cite · data as of 2026-10-05
Step 3.5 Flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/step-3-5-flash
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP