Rankings / Z.ai
GLM 4 6v
open weightsreleased 2025-12-08
BenchAtlas Index
as of 2026-07-14
thinking
rank #322
9 families · 5 categories · high
no reasoning
rank #381
9 families · 5 categories · high
Benchmark evidence
35 results
agentic coding
| τ²-Bench | thinking | 31.6 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 30.7 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | no reasoning | 41.1 % | independent | Artificial Analysis |
| LiveCodeBench v6 implementation=artificial-analysis | thinking | 16.0 % | independent | Artificial Analysis |
| SciCode | thinking | 30.4 % | independent | Artificial Analysis |
| SciCode | no reasoning | 27.2 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | thinking | 16.8 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 11.0 points | independent | Artificial Analysis |
| AA Math Index | thinking | 85.3 points | independent | Artificial Analysis |
| AA Math Index | no reasoning | 26.3 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1417.9 1392.6–1443.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1407.9 1388.6–1427.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1404.4 1382.6–1426.3 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1394.7 1378.4–1410.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1382.7 1367.4–1398.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1378.6 1355.3–1401.9 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1377.3 1366.0–1388.5 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1368.0 1346.0–1390.1 | 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 | 1368.0 1342.6–1393.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1358.8 1343.8–1373.7 | 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 | 1354.5 1330.7–1378.4 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1350.7 1334.7–1366.7 | 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 | 1349.3 1323.0–1375.7 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 71.9 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 56.6 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 8.9 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 3.7 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | thinking | 79.9 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | no reasoning | 75.2 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 40.3 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 12.3 % | independent | Artificial Analysis |
| IFBench | thinking | 30.1 % | independent | Artificial Analysis |
| IFBench | no reasoning | 27.9 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | thinking | 85.3 % | independent | Artificial Analysis |
| AIME year=2025 · implementation=artificial-analysis | no reasoning | 26.3 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + GLM 4 6v | Terminal-Bench Hard | 14.4 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GLM 4 6v | Terminal-Bench Hard | 3.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.