BenchAtlas

Rankings / zai

GLM 5v Turbo

proprietary

released 2026-04-01

BenchAtlas Index

as of 2026-07-14
56.7
thinking
rank #170
7 families · 4 categories · medium

Benchmark evidence

23 results
agentic coding
τ²-Benchthinking98.5 %independentArtificial Analysis
coding
SciCodethinking43.5 %independentArtificial Analysis
external indices
Intelligence Index v4.1thinking34.5 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1500.9
1483.2–1518.7
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1487.4
1472.5–1502.2
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1468.3
1451.0–1485.6
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1459.4
1447.6–1471.1
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1456.7
1442.9–1470.5
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1453.5
1438.9–1468.1
communityLMArena 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
1446.6
1423.0–1470.2
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1440.9
1431.5–1450.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1436.9
1413.8–1460.1
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1436.7
1423.9–1449.5
communityLMArena 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
1432.0
1411.5–1452.5
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1427.0
1410.7–1443.4
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1423.5
1411.0–1435.9
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1415.6
1396.6–1434.7
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1398.4
1378.6–1418.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1396.4
1373.4–1419.4
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
thinking80.9 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
thinking15.8 %independentArtificial Analysis
long context instruction
AA-LCRthinking61.0 %independentArtificial Analysis
IFBenchthinking61.1 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + GLM 5v TurboTerminal-Bench Hard32.6 %independentArtificial Analysis

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.