Step 3.7 Flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Updated 5 h ago · first seen 11 Sept 2026
model_01M294WVXWCJK3P3D3PV5X7Q3G
Overview
Identity
Identity block not returned by the API for this entity.
Openness
Openness not classified yet — no sourced evidence to place this model in the ontology.
Key facts
- Release date
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Architecture
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Capabilities
Modalities
- Modalities
- imagetextvideo
- Input
- imagetextvideo
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Benchmarks9
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
No benchmark results recorded
Providers & Pricing1
All offers in the price terminal →USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Output price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $1.1511 Sept 2026
Input price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $0.2011 Sept 2026
Timeline11
Full timeline →Step 3.7 Flash scores 35.61% on Terminal-Bench
artificial_analysisStep 3.7 Flash scores 39.33% on Terminal-Bench
artificial_analysisStep 3.7 Flash scores 98.54% on τ²-bench
artificial_analysisStep 3.7 Flash scores 75.32% on MMMU-Pro
artificial_analysisStep 3.7 Flash scores 67.28% on IFBench
artificial_analysisStep 3.7 Flash scores 43.87% on SciCode
artificial_analysisStep 3.7 Flash scores 21.41% on Humanity's Last Exam
artificial_analysisStep 3.7 Flash scores 19.48 on Artificial Analysis Intelligence Index
artificial_analysisOpenRouter lists Step 3.7 Flash at $0.2 in / $1.15 out per 1M tokens
openrouter
Change history16
Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 12 Sept 2026 20 claims in force
- Release date
- 28 May 2026
- Openness
- open-weights
- Context window
- 262.1K tokens
- Max output
- 230.4K tokens
- Modalities
- image, text, video
- Input modalities
- image, text, video
- Output modalities
- text
- Hugging Face repo
- stepfun-ai/Step-3.7-Flash
- Aa context window
- 262,144
- Aa openness
- open-weights
- Aa median output tokens per second
- 106.9
- Openrouter id
- stepfun/step-3.7-flash
- Openrouter listed at
- 28 May 2026
- Reasoning
- Yes
- Structured output
- Yes
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Tool calling
- Yes
- Vision
- Yes
- Weights available
- Yes
Release daterelease_date1
Opennessopenness1
Context windowcontext_length1
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Hugging Face repohf_repo1
Descriptiondescription1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
Openrouter idopenrouter_id1
Reasoningreasoning1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Visionvision1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
17
Source tiers
T217
Freshest observation
5 h ago
Conflicts
None
Source documents 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (56/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →