StepFun, open weights

Step 3.7 Flash

Step 3.7 Flash by StepFun ranks 207th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.3. Its strongest category is math, where it ranks 82nd. API pricing starts at $0.18 per million input tokens and $1.11 per million output tokens, with a 256K-token context window.

Last verified

Specifications

Noometry rank
#207 of 354
Index score
37.3
Evidence
Reported 5 results
Provider
StepFun
Released
May 29, 2026
Weights
Open weights
Reasoning
Yes
Context window
256K
Max output
256K
Input price
$0.18 / M
Output price
$1.11 / M
Blended price
$0.42 / M
Output speed
Not measured
Value
#72 of 219
Knowledge cutoff
March 2026
Input
text, image, video

Category scores

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

Step 3.7 Flash category scores
  1. Coding 40.0
  2. Reasoning 21.6
  3. Math 42.9
Step 3.7 Flash category ranks
CategoryScoreRankResults
Coding40.0#1501
Reasoning21.6#2192
Math42.9#821

Strengths and weaknesses

Categories where Step 3.7 Flash places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

Step 3.7 Flash: strongest categories
CategoryScorevs medianRank
Math42.9+6.3#82 of 327, top 26%

Weakest categories

Step 3.7 Flash: weakest categories
CategoryScorevs medianRank
Reasoning21.6−2.0#219 of 350, top 63%

Closest competitors

The models ranked just above and below Step 3.7 Flash. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Step 3.7 Flash
ModelRankScoreBlended $/MSpeed
Llama 3.1 Nemotron 70b Instruct#20337.6——Compare
MiniMax-M2#20437.4$0.5217Compare
Granite 4.1 8b#20537.4——Compare
Gemma 3n E4b IT#20637.3—13Compare
GPT-4.5#20837.2——Compare
Yi-Lightning#20937.1——Compare
Qwen Plus#21037.1$0.6037Compare
Gemini 2.5 Flash-Lite#21137.0$0.18172Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

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 3.7 Flash Coding benchmark results
BenchmarkScorePositionSettingSourceDate
SciCode40%#81 of 121, top 67%Epoch AI
ALE-Bench694.12#70 of 105, top 67%Epoch AI

Reasoning

Step 3.7 Flash Reasoning benchmark results
BenchmarkScorePositionSettingSourceDate
NYT Connections (extended)39.7%#67 of 91, top 74%high reasoningLech Mazur benchmarks
CritPt2.3%#71 of 134, top 53%Epoch AI

Math

Step 3.7 Flash Math benchmark results
BenchmarkScorePositionSettingSourceDate
MathArena Final-Answer Competitions68.5%#14 of 29, top 49%MathArena

API pricing by provider

Step 3.7 Flash API prices
RouteInput $/MOutput $/MCached input $/MChecked
deepinfra$0.20$1.15$0.042026-10-10
openrouter$0.20$1.15$0.042026-10-10
stepfun$0.18$1.11$0.0372026-10-10

Compare Step 3.7 Flash

Other StepFun models

Frequently asked questions

How good is Step 3.7 Flash?

Step 3.7 Flash by StepFun ranks 207th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.3. Its strongest category is math, where it ranks 82nd. API pricing starts at $0.18 per million input tokens and $1.11 per million output tokens, with a 256K-token context window.

How much does Step 3.7 Flash cost?

Step 3.7 Flash costs $0.18 per million input tokens and $1.11 per million output tokens on StepFun's own API, with cached input at $0.037.

What is Step 3.7 Flash's context window?

Step 3.7 Flash accepts up to 256K tokens of input and can write up to 256K tokens in one response.

Is Step 3.7 Flash open source?

Yes. Step 3.7 Flash's weights are downloadable from Hugging Face (stepfun-ai/Step-3.7-Flash); check the license for commercial terms.

What are Step 3.7 Flash's strengths and weaknesses?

Relative to other ranked models, Step 3.7 Flash places best in math and lowest in reasoning.

What is Step 3.7 Flash best at?

Its best category is math, where it ranks 82nd on Noometry.