BenchAtlas

Rankings / Alibaba

Qwen3 5 397B A17b

open weights

released 2026-02-16

BenchAtlas Index

as of 2026-07-14
55.4
thinking
rank #177
7 families · 4 categories · medium
50.2
no reasoning
rank #216
7 families · 4 categories · medium

Benchmark evidence

45 results
agentic coding
τ²-Benchthinking95.6 %independentArtificial Analysis
τ²-Benchno reasoning83.9 %independentArtificial Analysis
τ²-Bench
subset=banking
thinking13.4 %independentArtificial Analysis
coding
SciCodethinking42.0 %independentArtificial Analysis
SciCodeno reasoning41.1 %independentArtificial Analysis
external indices
AA Coding Indexthinking48.2 pointsindependentArtificial Analysis
Intelligence Index v4.1thinking33.7 pointsindependentArtificial Analysis
Intelligence Index v4.1no reasoning32.0 pointsindependentArtificial Analysis
human preference
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1502.1
1489.6–1514.5
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1491.4
1485.5–1497.4
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1481.9
1473.0–1490.9
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1480.7
1475.5–1485.9
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1466.8
1461.2–1472.4
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
1466.7
1459.7–1473.7
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1465.3
1449.0–1481.6
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1463.8
1453.7–1473.8
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1463.5
1458.9–1468.0
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1459.2
1447.8–1470.6
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1454.4
1448.9–1459.9
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1452.6
1445.6–1459.6
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1449.4
1444.5–1454.2
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1449.0
1433.2–1464.7
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1445.4
1434.6–1456.1
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1445.3
1427.3–1463.3
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1444.7
1423.3–1466.1
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
1443.9
1437.3–1450.4
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1442.1
1438.4–1445.9
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1441.3
1436.2–1446.5
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1441.2
1431.3–1451.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1437.7
1429.2–1446.1
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1433.6
1428.9–1438.3
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1433.3
1427.7–1438.8
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1426.7
1398.1–1455.2
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
1424.0
1417.8–1430.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1408.0
1400.8–1415.2
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
1405.8
1399.3–1412.4
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1396.7
1375.1–1418.2
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
thinking89.3 %independentArtificial Analysis
GPQA Diamond
implementation=artificial-analysis
no reasoning86.1 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
thinking27.3 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
no reasoning18.8 %independentArtificial Analysis
long context instruction
AA-LCRthinking65.7 %independentArtificial Analysis
AA-LCRno reasoning58.0 %independentArtificial Analysis
IFBenchthinking78.8 %independentArtificial Analysis
IFBenchno reasoning51.6 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Qwen3 5 397B A17bTerminal-Bench 2.151.3 %independentArtificial Analysis
agent + model Artificial Analysis harness + Qwen3 5 397B A17bTerminal-Bench Hard40.9 %independentArtificial Analysis
agent + model Artificial Analysis harness + Qwen3 5 397B A17bTerminal-Bench Hard35.6 %independentArtificial Analysis

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