Rankings / Alibaba
Qwen3 VL 235B A22b Instruct
open weightsreleased 2025-09-23
BenchAtlas Index
as of 2026-09-11
base configuration
rank #374
9 families · 5 categories · high
Benchmark evidence
35 results
agentic coding
| τ²-Bench | 35.1 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 59.4 % | independent | Artificial Analysis | |
| SciCode | 35.9 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 9.9 points | independent | Artificial Analysis | |
| AA Math Index | 70.7 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1464.5 1451.5–1477.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1454.6 1444.4–1464.7 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1454.0 1430.2–1477.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1449.8 1437.0–1462.6 | 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 | 1440.8 1425.5–1456.1 | 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 | 1439.9 1426.1–1453.7 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1439.3 1414.3–1464.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1438.5 1429.8–1447.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1435.8 1413.1–1458.4 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1431.7 1407.1–1456.4 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1425.6 1416.3–1434.9 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1425.2 1410.7–1439.5 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1421.4 1408.6–1434.2 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1414.0 1407.4–1420.5 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1410.0 1398.7–1421.3 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1407.8 1384.9–1430.8 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1405.1 1384.7–1425.4 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1404.8 1380.4–1429.3 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1404.7 1378.2–1431.2 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1400.1 1390.8–1409.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1396.3 1388.0–1404.7 | 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 | 1386.8 1373.8–1399.8 | 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 | 1358.0 1343.4–1372.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1357.3 1340.3–1374.3 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 71.2 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 6.6 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 82.3 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 32.7 % | independent | Artificial Analysis | |
| IFBench | 42.6 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 70.7 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Qwen3 VL 235B A22b Instruct | Terminal-Bench Hard | 6.8 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.
