BenchAtlas

Rankings / Alibaba

Qwen3 6 Plus

released 2026-03-31

BenchAtlas Index

as of 2026-07-14
49.4
base configuration
rank #224
9 families · 4 categories · medium
45.1
base configuration
rank #256
15 families · 5 categories · high

Benchmark evidence

59 results
agentic coding
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
41.4 %independentLiveBench
τ²-Bench97.7 %independentArtificial Analysis
τ²-Bench
subset=banking
16.5 %independentArtificial Analysis
coding
Release 2026-06-25
tasks_counted=2 · livebench_version=2026-06-25
78.2 %independentLiveBench
SciCode40.7 %independentArtificial Analysis
data analysis
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
69.9 %independentLiveBench
external indices
AA Coding Index54.5 pointsindependentArtificial Analysis
Intelligence Index v4.139.6 pointsindependentArtificial Analysis
ECI149.1 pointsindependentEpoch AI Benchmarking Hub
Vals Index48.9 pointsindependentVals AI
factuality
SimpleQA Verified49.1 %independentEpoch AI Benchmarking Hub
2026-05-12
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1494.2
1487.5–1501.0
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1483.2
1468.5–1497.8
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1481.0
1475.1–1487.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1475.5
1469.0–1482.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1474.2
1464.0–1484.4
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1467.3
1462.2–1472.5
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1462.4
1444.9–1479.9
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1460.8
1448.8–1472.7
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1457.3
1433.4–1481.1
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1455.8
1450.1–1461.4
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1455.0
1448.9–1461.2
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1454.2
1441.3–1467.1
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1453.9
1441.3–1466.5
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
1453.5
1445.3–1461.7
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
1445.3
1437.7–1452.8
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1444.9
1436.9–1453.0
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1444.4
1433.1–1455.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1443.2
1438.8–1447.6
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1441.5
1435.8–1447.2
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1437.0
1427.4–1446.7
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1435.3
1428.9–1441.6
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1433.8
1416.3–1451.3
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1428.9
1408.4–1449.3
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1427.6
1422.2–1433.0
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
1424.7
1417.5–1431.9
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
1408.1
1400.5–1415.7
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1407.1
1398.5–1415.6
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1389.1
1365.6–1412.6
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
88.2 %independentArtificial Analysis
GPQA Diamond
implementation=vals-ai
87.4 %independentVals AI
GPQA Diamond87.4 %independentEpoch AI Benchmarking Hub
2026-05-12
Humanity's Last Exam
implementation=artificial-analysis
25.7 %independentArtificial Analysis
MMLU-Pro
implementation=vals-ai
87.7 %independentVals AI
language
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
75.0 %independentLiveBench
long context instruction
AA-LCR69.7 %independentArtificial Analysis
IFBench75.2 %independentArtificial Analysis
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
58.3 %independentLiveBench
multimodal
MMMU
implementation=vals-ai
84.2 %independentVals AI
professional
CaseLaw51.4 %independentVals AI
CorpFin61.9 %independentVals AI
LegalBench84.2 %independentVals AI
TaxEval74.7 %independentVals AI
reasoning math
AIME
implementation=vals-ai
94.6 %independentVals AI
FrontierMath26.2 %independentEpoch AI Benchmarking Hub
2026-05-12
FrontierMath Tier 4older version8.3 %independentEpoch AI Benchmarking Hub
2026-05-12
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
83.7 %independentLiveBench
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
75.8 %independentLiveBench
OTIS Mock AIME 2024–202590.6 %independentEpoch AI Benchmarking Hub
2026-05-12

Agent + model results

systems, not bare-model scores
agent + model Epoch Inspect harness + Qwen3 6 PlusSWE-bench Verified57.9 %independentEpoch AI Benchmarking Hub
agent + model Artificial Analysis harness + Qwen3 6 PlusTerminal-Bench 2.161.4 %independentArtificial Analysis
agent + model Artificial Analysis harness + Qwen3 6 PlusTerminal-Bench Hard43.9 %independentArtificial Analysis

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