Rankings / Alibaba
Qwen3 Coder 480B A35b Instruct
open weightsreleased 2025-07-22
BenchAtlas Index
as of 2026-09-11
base configuration
rank #342
11 families · 5 categories · high
Benchmark evidence
41 results
agentic coding
| τ²-Bench | 43.6 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 58.5 % | independent | Artificial Analysis | |
| SciCode | 35.9 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 11.9 points | independent | Artificial Analysis | |
| AA Math Index | 39.3 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1457.5 1448.5–1466.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1436.1 1428.9–1443.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1425.9 1417.1–1434.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1413.7 1407.2–1420.1 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1410.7 1394.5–1426.9 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1407.8 1399.0–1416.5 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1404.6 1390.1–1419.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1400.8 1385.4–1416.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1397.2 1387.6–1406.8 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1396.8 1390.3–1403.3 | 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 | 1395.8 1386.0–1405.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1391.8 1377.7–1405.9 | 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 | 1391.4 1381.9–1401.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1387.3 1382.3–1392.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1387.0 1363.5–1410.6 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1383.6 1375.7–1391.6 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1379.0 1363.3–1394.6 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1378.5 1362.0–1395.0 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1374.0 1359.3–1388.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1370.8 1364.8–1376.8 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1369.0 1353.9–1384.2 | 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 | 1366.2 1357.7–1374.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1363.6 1356.8–1370.4 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1362.3 1351.6–1373.1 | 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 | 1352.9 1343.8–1362.0 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1351.2 1325.8–1376.6 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1328.8 1303.3–1354.4 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1324.8 1304.0–1345.6 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 61.8 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 4.5 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 78.8 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 45.7 % | independent | Artificial Analysis | |
| IFBench | 40.5 % | independent | Artificial Analysis |
reasoning math
| AIME implementation=artificial-analysis | 47.7 % | independent | Artificial Analysis | |
| AIME year=2025 · implementation=artificial-analysis | 39.3 % | independent | Artificial Analysis | |
| MATH-500 implementation=artificial-analysis | 94.2 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model OpenHands + Qwen3 Coder 480B A35b Instruct | SWE-bench Verified | 69.6 % | unverified | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Qwen3 Coder 480B A35b Instruct | SWE-bench Verified | 55.4 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Qwen3 Coder 480B A35b Instruct | SWE-bench bash-only | 55.4 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Qwen3 Coder 480B A35b Instruct | SWE-bench Verified | 0.2 usd_per_task | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Qwen3 Coder 480B A35b Instruct | SWE-bench bash-only | 0.2 usd_per_task | community | SWE-bench Leaderboard |
| agent + model iflow-cli + Qwen3 Coder 480B A35b Instruct | Terminal-Bench 1.0 | 39.0 % | unverified | Terminal-Bench Leaderboard |
| agent + model Artificial Analysis harness + Qwen3 Coder 480B A35b Instruct | Terminal-Bench Hard | 18.9 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.