BenchAtlas

Rankings / Z.ai

GLM 4.7

released 2025-12-22

BenchAtlas Index

as of 2026-09-11
56.3
thinking
rank #191
9 families · 5 categories · high
49.0
base configuration
rank #247
4 families · 3 categories · medium
41.6
base configuration
rank #301
8 families · 3 categories · medium

Benchmark evidence

60 results
agentic coding
τ²-Benchthinking95.9 %independentArtificial Analysis
τ²-Benchno reasoning94.2 %independentArtificial Analysis
τ²-Bench
subset=banking
thinking12.2 %independentArtificial Analysis
coding
LiveCodeBench v6
implementation=artificial-analysis
thinking89.4 %independentArtificial Analysis
LiveCodeBench v6
implementation=artificial-analysis
no reasoning56.2 %independentArtificial Analysis
SciCodethinking45.1 %independentArtificial Analysis
SciCodeno reasoning35.4 %independentArtificial Analysis
external indices
AA Coding Indexthinking45.3 pointsindependentArtificial Analysis
Intelligence Index v4.1thinking22.2 pointsindependentArtificial Analysis
Intelligence Index v4.1no reasoning17.4 pointsindependentArtificial Analysis
AA Math Indexthinking95.0 pointsindependentArtificial Analysis
AA Math Indexno reasoning48.0 pointsindependentArtificial Analysis
ECI143.5 pointsindependentEpoch AI Benchmarking Hub
factuality
SimpleQA Verified32.2 %independentEpoch AI Benchmarking Hub
2026-08-27
SimpleQA Verified31.5 %independentEpoch AI Benchmarking Hub
2026-01-30
human preference
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1496.4
1477.6–1515.2
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1485.4
1473.3–1497.5
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1481.5
1460.9–1502.0
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1475.7
1466.2–1485.2
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1472.0
1460.5–1483.5
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
1471.5
1458.7–1484.4
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1462.0
1454.2–1469.9
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1461.6
1452.8–1470.4
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1458.6
1444.8–1472.3
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1453.3
1434.5–1472.0
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1449.5
1439.0–1460.1
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1445.0
1423.7–1466.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1441.8
1435.7–1447.9
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
1441.4
1429.1–1453.8
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1441.1
1432.5–1449.8
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1429.3
1415.2–1443.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1428.2
1406.8–1449.5
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1427.1
1416.7–1437.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1422.0
1398.3–1445.6
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1421.5
1413.9–1429.0
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
1415.4
1404.2–1426.6
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
1404.3
1392.4–1416.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1403.6
1390.2–1417.1
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
thinking85.9 %independentArtificial Analysis
GPQA Diamond83.3 %independentEpoch AI Benchmarking Hub
2026-01-29
GPQA Diamond
implementation=vals-ai
80.0 %independentVals AI
GPQA Diamond
implementation=artificial-analysis
no reasoning66.4 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
thinking27.4 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
no reasoning6.4 %independentArtificial Analysis
MMLU-Pro
implementation=artificial-analysis
thinking85.6 %independentArtificial Analysis
MMLU-Pro
implementation=vals-ai
82.7 %independentVals AI
MMLU-Pro
implementation=artificial-analysis
no reasoning79.4 %independentArtificial Analysis
long context instruction
AA-LCRthinking71.0 %independentArtificial Analysis
AA-LCRno reasoning40.7 %independentArtificial Analysis
IFBenchthinking67.9 %independentArtificial Analysis
IFBenchno reasoning54.6 %independentArtificial Analysis
professional
CaseLaw54.9 %independentVals AI
CorpFin46.4 %independentVals AI
LegalBench83.4 %independentVals AI
MedQA93.7 %independentVals AI
TaxEval68.8 %independentVals AI
reasoning math
AIME
year=2025 · implementation=artificial-analysis
thinking95.0 %independentArtificial Analysis
AIME
implementation=vals-ai
93.3 %independentVals AI
AIME
year=2025 · implementation=artificial-analysis
no reasoning48.0 %independentArtificial Analysis
OTIS Mock AIME 2024–202583.3 %independentEpoch AI Benchmarking Hub
2026-01-29

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + GLM 4.7Terminal-Bench 2.145.3 %independentArtificial Analysis
agent + model terminus-2 + GLM 4.7Terminal-Bench 2.033.4 %communityTerminal-Bench Leaderboard
agent + model Crux + GLM 4.7Terminal-Bench 2.033.3 %unverifiedTerminal-Bench Leaderboard
agent + model Artificial Analysis harness + GLM 4.7Terminal-Bench Hard31.8 %independentArtificial Analysis
agent + model Artificial Analysis harness + GLM 4.7Terminal-Bench Hard30.3 %independentArtificial Analysis

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

Related variants

GLM 5GLM 5.2GLM 5.1GLM 4.6GLM 4.5GLM 4 6vGLM 4 5vGLM 4 0520