Rankings / Z.ai
GLM 4.5
open weightsreleased 2025-07-28
BenchAtlas Index
as of 2026-07-14
base configuration
rank #261
8 families · 3 categories · medium
thinking
rank #265
11 families · 5 categories · high
Benchmark evidence
49 results
agentic coding
| τ²-Bench | thinking | 43.0 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | thinking | 73.8 % | independent | Artificial Analysis |
| SciCode | thinking | 34.8 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | thinking | 19.5 points | independent | Artificial Analysis |
| AA Math Index | thinking | 73.7 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1454.4 1445.7–1463.2 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1443.5 1436.5–1450.6 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1439.7 1423.1–1456.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1439.6 1421.9–1457.3 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1433.9 1417.6–1450.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1432.8 1426.4–1439.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1432.3 1424.2–1440.5 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1427.9 1403.2–1452.7 | 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 | 1421.8 1412.1–1431.6 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1419.5 1413.2–1425.8 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1417.9 1401.1–1434.7 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1416.6 1407.9–1425.2 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1415.6 1400.0–1431.2 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1413.2 1397.7–1428.7 | 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 | 1411.2 1401.9–1420.5 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1411.0 1406.1–1415.9 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1406.3 1396.5–1416.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1405.0 1397.1–1412.9 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1397.2 1391.1–1403.2 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1397.0 1390.2–1403.8 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1396.3 1380.1–1412.4 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1394.0 1370.0–1418.0 | 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 | 1383.5 1374.4–1392.7 | 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 | 1383.2 1374.7–1391.6 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1383.1 1367.9–1398.3 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1375.3 1349.3–1401.2 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1373.4 1362.5–1384.2 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1348.8 1323.9–1373.7 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 78.2 % | independent | Artificial Analysis |
| GPQA Diamond implementation=vals-ai | 72.2 % | independent | Vals AI | |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 12.2 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | thinking | 83.5 % | independent | Artificial Analysis |
| MMLU-Pro implementation=vals-ai | 81.2 % | independent | Vals AI |
long context instruction
| AA-LCR | thinking | 48.3 % | independent | Artificial Analysis |
| IFBench | thinking | 44.1 % | independent | Artificial Analysis |
professional
| CorpFin | 61.0 % | independent | Vals AI | |
| LegalBench | 75.6 % | independent | Vals AI | |
| MedQA | 90.0 % | independent | Vals AI | |
| TaxEval | 72.4 % | independent | Vals AI |
reasoning math
| AIME implementation=artificial-analysis | thinking | 87.3 % | independent | Artificial Analysis |
| AIME implementation=vals-ai | 86.7 % | independent | Vals AI | |
| AIME year=2025 · implementation=artificial-analysis | thinking | 73.7 % | independent | Artificial Analysis |
| MATH-500 implementation=artificial-analysis | thinking | 97.9 % | independent | Artificial Analysis |
| MATH-500 implementation=vals-ai | 94.0 % | independent | Vals AI |
Agent + model results
systems, not bare-model scores
| agent + model GLM-4.5 + GLM 4.5 | SWE-bench Verified | 64.2 % | unverified | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.5 | SWE-bench Verified | 54.2 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.5 | SWE-bench bash-only | 54.2 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.5 | SWE-bench bash-only | 0.3 usd_per_task | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.5 | SWE-bench Verified | 0.3 usd_per_task | community | SWE-bench Leaderboard |
| agent + model terminus-1 + GLM 4.5 | Terminal-Bench 1.0 | 39.9 % | community | Terminal-Bench Leaderboard |
| agent + model Artificial Analysis harness + GLM 4.5 | Terminal-Bench Hard | 22.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.