chore: import upstream snapshot with attribution
This commit is contained in:
@@ -0,0 +1,44 @@
|
||||
name = "Step 3.5 Flash 2603"
|
||||
description = "StepFun flash model for efficient multimodal reasoning, coding, and tool use"
|
||||
release_date = "2026-04-02"
|
||||
last_updated = "2026-04-02"
|
||||
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 = 34.6
|
||||
metric = "index"
|
||||
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SciCode"
|
||||
score = 38.5
|
||||
metric = "percent correct"
|
||||
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench Hard"
|
||||
score = 32.6
|
||||
metric = "success rate"
|
||||
source = "https://openrouter.ai/stepfun/step-3.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
@@ -0,0 +1,50 @@
|
||||
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"
|
||||
@@ -0,0 +1,82 @@
|
||||
name = "Step 3.7 Flash"
|
||||
description = "Newer StepFun flash model for faster agents, coding, and multimodal prompts"
|
||||
release_date = "2026-05-29"
|
||||
last_updated = "2026-05-29"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
knowledge = "2026-01-01"
|
||||
open_weights = true
|
||||
|
||||
[limit]
|
||||
context = 256_000
|
||||
input = 256_000
|
||||
output = 256_000
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
|
||||
[[weights]]
|
||||
label = "Hugging Face"
|
||||
url = "https://huggingface.co/stepfun-ai/Step-3.7-Flash"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 56.3
|
||||
metric = "resolve rate"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Verified"
|
||||
score = 76.5
|
||||
metric = "resolved"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench"
|
||||
score = 59.6
|
||||
metric = "success rate"
|
||||
version = "2.1"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Humanity's Last Exam"
|
||||
score = 47.2
|
||||
metric = "accuracy"
|
||||
variant = "with tools"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "BrowseComp"
|
||||
score = 75.8
|
||||
metric = "accuracy"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Toolathlon"
|
||||
score = 49.5
|
||||
metric = "success rate"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "GDPval"
|
||||
score = 45.8
|
||||
metric = "wins or ties"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "ClawEval"
|
||||
score = 67.1
|
||||
metric = "pass^3"
|
||||
version = "1.1"
|
||||
source = "https://static.stepfun.com/blog/step-3.7-flash/"
|
||||
date = "2026-05-29"
|
||||
Reference in New Issue
Block a user