Rankings / zai
GLM 4.5 Air
open weightsreleased 2025-07-28
BenchAtlas Index
as of 2026-09-11
base configuration
rank #326
10 families · 5 categories · high
Benchmark evidence
42 results
agentic coding
| τ²-Bench | 46.5 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 68.4 % | independent | Artificial Analysis | |
| SciCode | 30.6 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 11.1 points | independent | Artificial Analysis | |
| AA Math Index | 80.7 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1427.2 1419.5–1434.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1415.2 1409.0–1421.5 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1406.9 1394.2–1419.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1403.0 1395.5–1410.5 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1397.7 1370.3–1425.2 | 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 | 1396.5 1388.0–1405.1 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1394.2 1379.5–1408.8 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1390.7 1375.0–1406.4 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1390.5 1384.7–1396.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1390.4 1384.9–1395.9 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1390.0 1374.5–1405.5 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1388.5 1373.6–1403.5 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1378.9 1371.4–1386.5 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1376.3 1354.9–1397.8 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1373.2 1368.9–1377.4 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1372.5 1358.8–1386.2 | 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 | 1372.1 1363.9–1380.3 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1367.3 1358.7–1375.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1361.1 1354.3–1368.0 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1360.3 1347.5–1373.1 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1352.4 1347.2–1357.7 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1351.6 1329.3–1374.0 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1343.3 1337.3–1349.3 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1341.7 1327.2–1356.2 | 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 | 1340.3 1332.8–1347.7 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1331.5 1310.3–1352.8 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1326.9 1317.3–1336.6 | 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 | 1324.5 1316.4–1332.6 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1288.2 1264.5–1311.8 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 73.3 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 7.0 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 81.5 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 46.7 % | independent | Artificial Analysis | |
| IFBench | 37.5 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 80.7 % | independent | Artificial Analysis | |
| AIME implementation=artificial-analysis | 67.3 % | independent | Artificial Analysis | |
| MATH-500 implementation=artificial-analysis | 96.5 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + GLM 4.5 Air | Terminal-Bench Hard | 20.4 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.