Rankings / Alibaba
Qwen3 5 27B
open weightsreleased 2026-02-24
BenchAtlas Index
as of 2026-09-11
thinking
rank #184
7 families · 4 categories · medium
no reasoning
rank #237
7 families · 4 categories · medium
Benchmark evidence
40 results
agentic coding
| τ²-Bench | thinking | 93.9 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 87.1 % | independent | Artificial Analysis |
coding
| SciCode | thinking | 39.5 % | independent | Artificial Analysis |
| SciCode | no reasoning | 36.7 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | thinking | 22.9 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 19.4 points | independent | Artificial Analysis |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1465.9 1451.6–1480.2 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1449.7 1442.4–1457.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1445.0 1438.7–1451.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1441.8 1434.7–1449.0 | 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 | 1439.7 1430.6–1448.7 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1438.7 1426.5–1450.9 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1434.4 1419.1–1449.8 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1428.5 1414.0–1443.1 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1428.0 1414.2–1441.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1426.5 1421.2–1431.9 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1426.2 1420.2–1432.1 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1421.5 1414.9–1428.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1414.1 1405.0–1423.3 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1413.5 1391.6–1435.4 | 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 | 1408.4 1399.9–1416.8 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1408.0 1403.6–1412.4 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1406.6 1393.4–1419.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1400.5 1393.7–1407.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1400.3 1380.5–1420.2 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1393.0 1382.1–1403.9 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1391.5 1385.5–1397.5 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1386.4 1380.9–1391.8 | 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 | 1379.4 1371.5–1387.4 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1368.6 1343.0–1394.1 | 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 | 1359.6 1350.8–1368.3 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1356.2 1346.5–1366.0 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 85.8 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 84.2 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 23.9 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 13.9 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 77.7 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 64.0 % | independent | Artificial Analysis |
| IFBench | thinking | 75.6 % | independent | Artificial Analysis |
| IFBench | no reasoning | 46.9 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Qwen3 5 27B | Terminal-Bench Hard | 32.6 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Qwen3 5 27B | Terminal-Bench Hard | 31.8 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.