name = "Step 3.5 Flash"
description = "StepFun flash lane for quick multimodal reasoning and coding assistance"
release_date = "2026-01-29"
last_updated = "2026-02-13"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-01"
open_weights = true

[limit]
context = 256_000
input = 256_000
output = 256_000

[modalities]
input = ["text"]
output = ["text"]

[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/stepfun-ai/Step-3.5-Flash"

[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 31.6
metric = "index"
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
date = "2026-06-02"

[[benchmarks]]
name = "SciCode"
score = 40.4
metric = "percent correct"
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
date = "2026-06-02"

[[benchmarks]]
name = "Terminal-Bench Hard"
score = 27.3
metric = "success rate"
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
date = "2026-06-02"

[[benchmarks]]
name = "SWE-Bench Verified"
score = 74.4
metric = "resolved"
source = "https://arxiv.org/abs/2602.10604"