Rankings / Z.ai
GLM 4.6
released 2025-09-30
BenchAtlas Index
as of 2026-09-11
thinking
rank #265
10 families · 5 categories · high
base configuration
rank #272
6 families · 3 categories · medium
no reasoning
rank #340
10 families · 5 categories · high
Benchmark evidence
60 results
agentic coding
| τ²-Bench | no reasoning | 76.9 % | independent | Artificial Analysis |
| τ²-Bench | thinking | 70.5 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | thinking | 13.4 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | thinking | 69.5 % | independent | Artificial Analysis |
| LiveCodeBench v6 implementation=artificial-analysis | no reasoning | 56.1 % | independent | Artificial Analysis |
| SciCode | thinking | 38.4 % | independent | Artificial Analysis |
| SciCode | no reasoning | 33.1 % | independent | Artificial Analysis |
external indices
| AA Coding Index | thinking | 45.8 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | thinking | 18.5 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 14.9 points | independent | Artificial Analysis |
| AA Math Index | thinking | 86.0 points | independent | Artificial Analysis |
| AA Math Index | no reasoning | 44.3 points | independent | Artificial Analysis |
| ECI | 140.8 points | independent | Epoch AI Benchmarking Hub |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1478.2 1466.4–1489.9 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1457.9 1450.7–1465.2 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1452.8 1446.9–1458.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1449.5 1442.5–1456.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1448.5 1434.7–1462.3 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1446.5 1423.3–1469.8 | 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 | 1446.0 1438.0–1454.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1441.5 1436.5–1446.6 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1440.8 1427.5–1454.0 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1440.5 1426.4–1454.7 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1436.8 1431.4–1442.3 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1434.8 1422.7–1446.9 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1430.7 1424.1–1437.4 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1424.8 1420.9–1428.8 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1424.5 1402.0–1446.9 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1420.8 1404.2–1437.5 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1420.6 1412.3–1428.9 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1417.3 1404.5–1430.2 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1416.5 1410.9–1422.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1413.6 1407.2–1420.0 | 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 | 1411.9 1404.3–1419.5 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1410.5 1391.2–1429.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1408.3 1403.4–1413.2 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1406.8 1397.0–1416.7 | 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 | 1404.5 1397.4–1411.5 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1400.9 1392.3–1409.5 | 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 | 1394.0 1386.5–1401.6 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1377.4 1352.4–1402.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 78.0 % | independent | Artificial Analysis |
| GPQA Diamond implementation=vals-ai | 74.5 % | independent | Vals AI | |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 63.2 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 14.5 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 5.5 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | thinking | 82.9 % | independent | Artificial Analysis |
| MMLU-Pro implementation=vals-ai | 82.2 % | independent | Vals AI | |
| MMLU-Pro implementation=artificial-analysis | no reasoning | 78.4 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 54.0 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 28.3 % | independent | Artificial Analysis |
| IFBench | thinking | 43.4 % | independent | Artificial Analysis |
| IFBench | no reasoning | 36.7 % | independent | Artificial Analysis |
professional
| CorpFin | 56.8 % | independent | Vals AI | |
| LegalBench | 79.6 % | independent | Vals AI | |
| MedQA | 92.2 % | independent | Vals AI | |
| TaxEval | 66.2 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 92.7 % | independent | Vals AI | |
| AIME year=2025 · implementation=artificial-analysis | thinking | 86.0 % | independent | Artificial Analysis |
| AIME year=2025 · implementation=artificial-analysis | no reasoning | 44.3 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model GLM-4.6 + GLM 4.6 | SWE-bench Verified | 68.2 % | unverified | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.6 | SWE-bench bash-only | 55.4 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.6 | SWE-bench Verified | 55.4 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.6 | SWE-bench Verified | 0.1 usd_per_task | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GLM 4.6 | SWE-bench bash-only | 0.1 usd_per_task | community | SWE-bench Leaderboard |
| agent + model Artificial Analysis harness + GLM 4.6 | Terminal-Bench 2.1 | 49.4 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GLM 4.6 | Terminal-Bench Hard | 28.8 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GLM 4.6 | Terminal-Bench Hard | 25.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.