BenchAtlas

Rankings / stepfun

Step 3.5 Flash

open weights

released 2026-04-02

BenchAtlas Index

as of 2026-07-14
54.7
base configuration
rank #183
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 v4.126.0 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1449.8
1443.81455.9
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1437.0
1431.71442.2
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1436.3
1423.71449.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1431.9
1422.41441.4
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1425.2
1419.41431.0
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1419.5
1407.51431.5
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1413.6
1397.01430.2
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1413.6
1409.01418.1
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1410.3
1405.41415.2
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1407.4
1396.51418.3
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1407.0
1401.51412.6
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1407.0
1391.11422.8
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
1406.1
1399.01413.2
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1399.4
1388.91409.9
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1397.4
1390.51404.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1395.2
1391.51398.9
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1394.2
1384.21404.2
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
1388.7
1382.11395.3
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1387.7
1382.21393.3
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1380.9
1360.11401.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1377.1
1368.91385.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1375.8
1371.21380.3
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1374.0
1368.81379.1
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
1366.4
1360.21372.5
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1363.2
1345.71380.7
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
1349.7
1343.01356.4
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1348.0
1320.81375.1
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1347.4
1340.21354.7
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1338.3
1317.41359.1
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
82.6 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
22.6 %independentArtificial Analysis
long context instruction
AA-LCR54.3 %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.