Rankings / Alibaba
Qwen3 Max Preview
proprietaryreleased 2025-09-05
BenchAtlas Index
as of 2026-07-14
base configuration
rank #276
5 families · 3 categories · medium
base configuration
rank #291
9 families · 5 categories · high
Benchmark evidence
45 results
agentic coding
| τ²-Bench | 32.8 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 65.1 % | independent | Artificial Analysis | |
| SciCode | 37.0 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 19.2 points | independent | Artificial Analysis | |
| AA Math Index | 75.0 points | independent | Artificial Analysis |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1488.7 1473.1–1504.4 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1481.8 1473.4–1490.1 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1473.6 1457.6–1489.5 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1470.1 1463.4–1476.7 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1469.0 1452.2–1485.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1459.2 1453.4–1465.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1457.2 1449.7–1464.7 | community | LMArena 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 | 1456.7 1447.3–1466.1 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1451.7 1429.5–1473.9 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1450.9 1425.3–1476.5 | community | LMArena 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 | 1445.6 1437.0–1454.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1445.1 1436.1–1454.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1443.9 1435.9–1451.9 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1440.5 1424.7–1456.4 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1438.9 1433.0–1444.7 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1438.7 1423.8–1453.6 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1434.8 1430.3–1439.3 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1431.8 1425.4–1438.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1431.1 1417.1–1445.2 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1427.6 1411.2–1444.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1426.8 1419.5–1434.1 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1426.1 1420.4–1431.8 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1419.8 1404.2–1435.4 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1405.8 1398.0–1413.6 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1397.5 1388.9–1406.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1394.0 1384.0–1404.0 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1383.0 1358.8–1407.1 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=vals-ai | 77.8 % | independent | Vals AI | |
| GPQA Diamond implementation=artificial-analysis | 76.4 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 9.3 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 83.8 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | 83.5 % | independent | Vals AI |
long context instruction
| AA-LCR | 39.7 % | independent | Artificial Analysis | |
| IFBench | 48.0 % | independent | Artificial Analysis |
professional
| CorpFin | 53.0 % | independent | Vals AI | |
| LegalBench | 80.3 % | independent | Vals AI | |
| MedQA | 87.4 % | independent | Vals AI | |
| TaxEval | 74.0 % | independent | Vals AI |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 75.0 % | independent | Artificial Analysis | |
| AIME implementation=vals-ai | 60.7 % | independent | Vals AI |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Qwen3 Max Preview | Terminal-Bench Hard | 19.7 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.