Rankings / Alibaba
Qwen3 5 122B A10b
open weightsreleased 2026-02-24
BenchAtlas Index
as of 2026-09-11
thinking
rank #226
7 families · 4 categories · medium
no reasoning
rank #283
7 families · 4 categories · medium
Benchmark evidence
45 results
agentic coding
| τ²-Bench | thinking | 93.6 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 84.5 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | thinking | 15.3 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | no reasoning | 10.3 % | independent | Artificial Analysis |
coding
| SciCode | thinking | 39.7 % | independent | Artificial Analysis |
| SciCode | no reasoning | 35.6 % | independent | Artificial Analysis |
external indices
| AA Coding Index | thinking | 45.7 points | independent | Artificial Analysis |
| AA Coding Index | no reasoning | 43.3 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 17.7 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | thinking | 16.2 points | independent | Artificial Analysis |
| ECI | no reasoning | 146.3 points | independent | Epoch AI Benchmarking Hub |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1461.7 1447.7–1475.7 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1459.4 1452.1–1466.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1450.8 1444.5–1457.0 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1448.8 1427.9–1469.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1445.9 1438.8–1453.1 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1444.8 1432.8–1456.8 | 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 | 1435.7 1426.8–1444.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1433.0 1427.6–1438.3 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1432.6 1419.2–1446.0 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1432.0 1426.1–1437.9 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1427.9 1412.8–1443.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1424.3 1411.5–1437.2 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1423.9 1409.9–1438.0 | 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 | 1422.3 1413.9–1430.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1418.4 1411.9–1424.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1417.2 1412.8–1421.5 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1417.0 1408.2–1425.9 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1411.3 1391.7–1430.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1407.0 1400.2–1413.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1404.5 1398.6–1410.5 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1396.9 1391.5–1402.3 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1396.6 1385.9–1407.2 | 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 | 1388.2 1380.5–1396.0 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1383.6 1359.6–1407.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1366.7 1357.2–1376.2 | 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 | 1366.0 1357.5–1374.5 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 85.7 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 82.7 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 25.2 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 15.9 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 76.3 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 61.3 % | independent | Artificial Analysis |
| IFBench | thinking | 75.7 % | independent | Artificial Analysis |
| IFBench | no reasoning | 50.8 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Qwen3 5 122B A10b | Terminal-Bench 2.1 | 47.6 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Qwen3 5 122B A10b | Terminal-Bench 2.1 | 47.2 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Qwen3 5 122B A10b | Terminal-Bench Hard | 31.1 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Qwen3 5 122B A10b | Terminal-Bench Hard | 29.6 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.