BenchAtlas

Rankings / stepfun

Step 3.5 Flash

open weights

released 2026-04-02

BenchAtlas Index

as of 2026-09-11
54.7
base configuration
rank #201
7 families · 4 categories · medium

Benchmark evidence

36 results
agentic coding
τ²-Bench87.4 %independentArtificial Analysis
coding
SciCode38.5 %independentArtificial Analysis
external indices
Intelligence Index v4.117.0 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1450.5
1444.61456.3
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1437.9
1432.81442.9
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1434.7
1423.61445.7
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1429.7
1420.91438.6
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1424.5
1418.71430.2
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1420.8
1409.41432.2
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1413.6
1409.21418.0
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1411.2
1395.91426.5
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1409.7
1404.91414.6
communityLMArena Leaderboard Dataset
Industry Life And Physical And Social Science (style control)older version
arena=text · category=industry_life_and_physical_and_social_science · style_control=true
1406.5
1399.71413.3
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1406.2
1395.61416.7
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1405.2
1399.91410.6
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1404.0
1389.71418.3
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1398.2
1388.21408.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1396.0
1389.41402.7
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1394.8
1385.31404.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1394.4
1390.81398.0
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1391.0
1371.61410.4
communityLMArena Leaderboard Dataset
Industry Business And Management And Financial Operations (style control)older version
arena=text · category=industry_business_and_management_and_financial_operations · style_control=true
1390.0
1383.61396.4
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1385.1
1379.71390.5
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1376.3
1368.61383.9
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1375.6
1371.21379.9
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1373.0
1368.11378.0
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1366.0
1360.11372.0
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1365.0
1348.31381.7
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1350.4
1325.51375.3
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1349.8
1343.41356.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1345.3
1338.31352.3
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1336.4
1316.71356.0
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
82.6 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
24.5 %independentArtificial Analysis
long context instruction
AA-LCR63.0 %independentArtificial Analysis
IFBench66.5 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Step 3.5 FlashTerminal-Bench Hard32.6 %independentArtificial Analysis

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.