StepFun, open weights

# Step 3.5 Flash

> Step 3.5 Flash by StepFun, released January 2026. Ranked #116 of 354 with a Noometry Index of 42.3. API: $0.10 in / $0.30 out per M tokens. 256K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/step-3-5-flash
- Last updated: 2026-10-10
- Title: Step 3.5 Flash Benchmarks, Price & Rank (October 2026)

Step 3.5 Flash by StepFun ranks 116th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.3. Its strongest category is math, where it ranks 84th. API pricing starts at $0.10 per million input tokens and $0.30 per million output tokens, with a 256K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #116 of 354
- **Index score:** 42.3
- **Evidence:** Confirmed 19 results
- **Provider:** [![](/logos/stepfun.svg) StepFun](https://noometry.com/providers/stepfun)
- **Released:** January 29, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 256K
- **Max output:** 256K
- **Input price:** $0.10 / M
- **Output price:** $0.30 / M
- **Blended price:** $0.15 / M
- **Output speed:** Not measured
- **Value:** #23 of 219
- **Knowledge cutoff:** January 2025
- **Input:** text
- **Hugging Face:** [stepfun-ai/Step-3.5-Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash)

## Category scores

Each category score combines every public result we have in that category.

Step 3.5 Flash category scores

1.  Coding 42.4
2.  Reasoning 22.2
3.  Math 42.6
4.  Knowledge 39.6
5.  Multilingual 50.5
6.  Instruction Following 73.1
7.  Long Context 42.8
8.  Writing & Preference 58.8
9.  020406080

Step 3.5 Flash category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 42.4 | #105 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 22.2 | #202 | 2 |
| [Math](https://noometry.com/best/math) | 42.6 | #84 | 2 |
| [Knowledge](https://noometry.com/best/knowledge) | 39.6 | #132 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 50.5 | #119 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 73.1 | #124 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 42.8 | #117 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 58.8 | #113 | 3 |

## Strengths and weaknesses

Categories where Step 3.5 Flash places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Step 3.5 Flash: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 42.6 | +6.1 | #84 of 327, top 26% |
| [Coding](https://noometry.com/best/coding) | 42.4 | +3.6 | #105 of 340, top 31% |
| [Writing & Preference](https://noometry.com/best/writing) | 58.8 | +5.0 | #113 of 312, top 37% |

### Weakest categories

Step 3.5 Flash: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 22.2 | −1.4 | #202 of 350, top 58% |
| [Knowledge](https://noometry.com/best/knowledge) | 39.6 | +2.3 | #132 of 314, top 43% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 73.1 | +1.8 | #124 of 305, top 41% |

## Closest competitors

The models ranked just above and below Step 3.5 Flash. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Step 3.5 Flash
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen3.5-Flash](https://noometry.com/models/qwen3-5-flash) | #112 | 42.5 | $0.18 | — | [Compare](https://noometry.com/compare/qwen3-5-flash-vs-step-3-5-flash) |
| [Nemotron 3 Ultra](https://noometry.com/models/nemotron-3-ultra) | #113 | 42.5 | $0.93 | — | [Compare](https://noometry.com/compare/nemotron-3-ultra-vs-step-3-5-flash) |
| [Hunyuan T1 20250711](https://noometry.com/models/hunyuan-t1) | #114 | 42.5 | — | — | [Compare](https://noometry.com/compare/hunyuan-t1-vs-step-3-5-flash) |
| [DeepSeek-R1](https://noometry.com/models/deepseek-r1) | #115 | 42.3 | $0.91 | 10 | [Compare](https://noometry.com/compare/deepseek-r1-vs-step-3-5-flash) |
| [Qwen3.6 27B](https://noometry.com/models/qwen3-6-27b) | #117 | 42.2 | $1.35 | — | [Compare](https://noometry.com/compare/qwen3-6-27b-vs-step-3-5-flash) |
| [Amazon Nova Experimental Chat 10 20](https://noometry.com/models/amazon-nova-experimental-chat-10-20) | #118 | 42.1 | — | — | [Compare](https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-step-3-5-flash) |
| [Qwen3.5 122B-A10B](https://noometry.com/models/qwen3-5-122b-a10b) | #119 | 42.1 | $1.10 | — | [Compare](https://noometry.com/compare/qwen3-5-122b-a10b-vs-step-3-5-flash) |
| [Longcat Flash Chat](https://noometry.com/models/longcat-flash-chat) | #120 | 42.1 | — | 69 | [Compare](https://noometry.com/compare/longcat-flash-chat-vs-step-3-5-flash) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Step 3.5 Flash Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1436 | #103 of 294, top 36% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Reasoning

Step 3.5 Flash Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 28.4% | #74 of 91, top 82% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1411 | #117 of 297, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

Step 3.5 Flash Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [MathArena Final-Answer Competitions](https://noometry.com/benchmarks/matharena) | 66.8% | #19 of 29, top 66% |  | [MathArena](https://matharena.ai/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1408 | #113 of 285, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Step 3.5 Flash Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1421 | #105 of 273, top 39% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Step 3.5 Flash Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1385 | #119 of 297, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1447 | #106 of 285, top 38% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1421 | #98 of 223, top 44% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1405 | #91 of 231, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1354 | #94 of 211, top 45% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1352 | #104 of 213, top 49% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1385 | #124 of 283, top 44% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1419 | #93 of 226, top 42% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Step 3.5 Flash Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1385 | #119 of 298, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Step 3.5 Flash Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1402 | #115 of 291, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Step 3.5 Flash Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1403 | #117 of 297, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1357 | #124 of 295, top 43% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1405 | #116 of 295, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Step 3.5 Flash API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [openrouter](https://openrouter.ai/stepfun/step-3.5-flash) | $0.10 | $0.30 | — | 2026-10-10 |
| [stepfun](https://platform.stepfun.ai/docs/en/overview/concept) | $0.10 | $0.30 | $0.02 | 2026-10-10 |

[All StepFun API prices →](https://noometry.com/llm-pricing/stepfun) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Step 3.5 Flash

-   [Step 3.5 Flash vs DeepSeek-R1](https://noometry.com/compare/deepseek-r1-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Qwen3.6 27B](https://noometry.com/compare/qwen3-6-27b-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Hunyuan T1 20250711](https://noometry.com/compare/hunyuan-t1-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Amazon Nova Experimental Chat 10 20](https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Nemotron 3 Ultra](https://noometry.com/compare/nemotron-3-ultra-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Qwen3.5 122B-A10B](https://noometry.com/compare/qwen3-5-122b-a10b-vs-step-3-5-flash)
-   [Step 3.5 Flash vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Qwen3.8 Max](https://noometry.com/compare/qwen3-8-max-vs-step-3-5-flash)
-   [Step 3.5 Flash vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-step-3-5-flash)
-   [Step 3.5 Flash vs Muse Spark 1.3](https://noometry.com/compare/muse-spark-1-3-vs-step-3-5-flash)

## Other StepFun models

-   [Step 5 Preview](https://noometry.com/models/step-5-preview)47.9
-   [Step 3](https://noometry.com/models/step-3)40.5
-   [Step 1o Turbo 202506](https://noometry.com/models/step-1o-turbo-202506)39.7
-   [Step 2 16k Exp 202412](https://noometry.com/models/step-2-16k-exp-202412)39.2
-   [Step 3.7 Flash](https://noometry.com/models/step-3-7-flash)37.3
-   [Step 1 (32K)](https://noometry.com/models/step-1)
-   [Step 2 (16K)](https://noometry.com/models/step-2)

## Frequently asked questions

### How good is Step 3.5 Flash?

Step 3.5 Flash by StepFun ranks 116th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.3. Its strongest category is math, where it ranks 84th. API pricing starts at $0.10 per million input tokens and $0.30 per million output tokens, with a 256K-token context window.

### How much does Step 3.5 Flash cost?

Step 3.5 Flash costs $0.10 per million input tokens and $0.30 per million output tokens on StepFun's own API, with cached input at $0.02.

### What is Step 3.5 Flash's context window?

Step 3.5 Flash accepts up to 256K tokens of input and can write up to 256K tokens in one response.

### Is Step 3.5 Flash open source?

Yes. Step 3.5 Flash's weights are downloadable from Hugging Face (stepfun-ai/Step-3.5-Flash); check the license for commercial terms.

### What are Step 3.5 Flash's strengths and weaknesses?

Relative to other ranked models, Step 3.5 Flash places best in math, coding, writing & preference and lowest in reasoning, knowledge, instruction following.

### What is Step 3.5 Flash best at?

Its best category is math, where it ranks 84th on Noometry.

### Cite this page

Noometry. (2026). Step 3.5 Flash benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/step-3-5-flash

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/step-3-5-flash.md).