Rankings / Z.ai
GLM 4 5v
open weightsreleased 2025-08-11
BenchAtlas Index
as of 2026-07-14
thinking
rank #380
9 families · 5 categories · high
no reasoning
rank #412
9 families · 5 categories · high
Benchmark evidence
38 results
agentic coding
| τ²-Bench | thinking | 22.5 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 19.6 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | thinking | 60.4 % | independent | Artificial Analysis |
| LiveCodeBench v6 implementation=artificial-analysis | no reasoning | 35.2 % | independent | Artificial Analysis |
| SciCode | thinking | 22.1 % | independent | Artificial Analysis |
| SciCode | no reasoning | 18.8 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | thinking | 9.1 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 7.0 points | independent | Artificial Analysis |
| AA Math Index | thinking | 73.0 points | independent | Artificial Analysis |
| AA Math Index | no reasoning | 15.3 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1404.1 1385.7–1422.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1397.1 1380.6–1413.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1396.4 1382.6–1410.2 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1380.7 1368.8–1392.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1375.5 1363.6–1387.5 | 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 | 1360.2 1338.5–1381.9 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1358.3 1338.6–1378.1 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1353.6 1345.2–1361.9 | 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 | 1342.2 1323.0–1361.4 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1341.8 1325.9–1357.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1341.7 1323.7–1359.8 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1323.3 1311.8–1334.8 | 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 | 1320.8 1302.0–1339.5 | 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 | 1320.2 1302.7–1337.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1313.9 1301.7–1326.2 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1310.9 1288.3–1333.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 68.4 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 57.3 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 5.9 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 3.6 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | thinking | 78.8 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | no reasoning | 75.1 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 0.0 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 0.0 % | independent | Artificial Analysis |
| IFBench | thinking | 34.2 % | independent | Artificial Analysis |
| IFBench | no reasoning | 28.6 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | thinking | 73.0 % | independent | Artificial Analysis |
| AIME year=2025 · implementation=artificial-analysis | no reasoning | 15.3 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + GLM 4 5v | Terminal-Bench Hard | 6.8 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GLM 4 5v | Terminal-Bench Hard | 5.3 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.