Rankings / Alibaba
Qwen2 5 72B Instruct
released 2024-09-19
BenchAtlas Index
as of 2026-09-11
base configuration
rank #439
12 families · 5 categories · high
Benchmark evidence
43 results
agentic coding
| τ²-Bench | 34.5 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 27.6 % | independent | Artificial Analysis | |
| SciCode | 26.7 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 7.7 points | independent | Artificial Analysis | |
| AA Math Index | 14.0 points | independent | Artificial Analysis | |
| ECI | 129.0 points | independent | Epoch AI Benchmarking Hub |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1355.3 1347.6–1362.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1343.0 1336.4–1349.6 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1330.8 1317.9–1343.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1326.0 1318.2–1333.8 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1322.4 1311.3–1333.5 | 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 | 1318.1 1310.1–1326.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1317.1 1310.8–1323.5 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1316.8 1308.7–1324.9 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1315.8 1310.6–1321.0 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1313.0 1298.9–1327.0 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1309.4 1300.6–1318.2 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1302.6 1298.6–1306.7 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1299.1 1291.2–1307.0 | 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 | 1299.1 1289.7–1308.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1296.6 1288.1–1305.1 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1296.1 1287.9–1304.4 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1294.8 1282.6–1307.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1292.0 1286.3–1297.7 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1285.0 1279.6–1290.5 | 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 | 1281.8 1275.0–1288.6 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1265.6 1246.4–1284.8 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1253.9 1245.4–1262.4 | 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 | 1244.3 1236.2–1252.4 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1237.2 1230.7–1243.7 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1229.4 1201.5–1257.2 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1210.5 1189.3–1231.7 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 49.1 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| GPQA Diamond implementation=artificial-analysis | 49.1 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 3.6 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 72.0 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 20.0 % | independent | Artificial Analysis | |
| IFBench | 36.9 % | independent | Artificial Analysis |
reasoning math
| AIME implementation=artificial-analysis | 16.0 % | independent | Artificial Analysis | |
| AIME year=2025 · implementation=artificial-analysis | 14.0 % | independent | Artificial Analysis | |
| MATH-500 implementation=artificial-analysis | 85.8 % | independent | Artificial Analysis | |
| MATH Level 5 | 63.2 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 8.1 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Qwen2 5 72B Instruct | Terminal-Bench Hard | 4.5 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.