BenchAtlas

Rankings / Z.ai

GLM 5.1

released 2026-04-07

BenchAtlas Index

as of 2026-07-14
61.1
thinking
rank #130
8 families · 4 categories · medium
58.6
base configuration
rank #155
5 families · 3 categories · medium
56.3
base configuration
rank #173
8 families · 3 categories · medium

Benchmark evidence

56 results
agentic coding
τ²-Benchthinking97.7 %independentArtificial Analysis
τ²-Benchno reasoning97.1 %independentArtificial Analysis
τ²-Bench
subset=banking
thinking11.6 %independentArtificial Analysis
coding
SciCodethinking43.8 %independentArtificial Analysis
SciCodeno reasoning36.1 %independentArtificial Analysis
external indices
AA Coding Indexthinking55.8 pointsindependentArtificial Analysis
Intelligence Index v4.1thinking40.2 pointsindependentArtificial Analysis
Intelligence Index v4.1no reasoning35.4 pointsindependentArtificial Analysis
ECI150.4 pointsindependentEpoch AI Benchmarking Hub
Vals Index52.5 pointsindependentVals AI
factuality
SimpleQA Verified37.3 %independentEpoch AI Benchmarking Hub
2026-05-01
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1521.7
1514.0–1529.4
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1517.7
1501.6–1533.9
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1511.0
1504.4–1517.6
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1504.4
1497.2–1511.6
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1497.5
1485.4–1509.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1494.1
1488.5–1499.7
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
1489.7
1480.4–1499.0
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1488.4
1467.4–1509.4
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1487.8
1481.7–1494.0
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1486.4
1472.4–1500.4
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1485.6
1479.0–1492.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1485.3
1475.7–1494.9
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1482.3
1466.3–1498.3
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1479.5
1473.3–1485.8
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1479.3
1463.3–1495.3
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1477.3
1463.8–1490.9
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1471.9
1467.1–1476.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1470.3
1458.8–1481.7
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
1465.4
1456.7–1474.0
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1465.0
1457.9–1472.0
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
1459.7
1451.7–1467.7
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1458.2
1433.1–1483.3
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1456.5
1436.2–1476.7
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1454.4
1444.8–1464.0
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1453.4
1447.6–1459.3
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
1447.2
1438.5–1455.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
thinking86.8 %independentArtificial Analysis
GPQA Diamond85.5 %independentEpoch AI Benchmarking Hub
2026-05-06
GPQA Diamond
implementation=vals-ai
84.5 %independentVals AI
GPQA Diamond
implementation=artificial-analysis
no reasoning83.9 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
thinking28.0 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
no reasoning25.6 %independentArtificial Analysis
MMLU-Pro
implementation=vals-ai
86.9 %independentVals AI
long context instruction
AA-LCRthinking62.3 %independentArtificial Analysis
AA-LCRno reasoning44.3 %independentArtificial Analysis
IFBenchthinking76.3 %independentArtificial Analysis
IFBenchno reasoning52.0 %independentArtificial Analysis
professional
CaseLaw51.6 %independentVals AI
CorpFin64.5 %independentVals AI
LegalBench84.4 %independentVals AI
TaxEval71.2 %independentVals AI
reasoning math
AIME
implementation=vals-ai
91.9 %independentVals AI
FrontierMath33.5 %independentEpoch AI Benchmarking Hub
2026-05-11
FrontierMath Tier 4older version12.5 %independentEpoch AI Benchmarking Hub
2026-05-12
OTIS Mock AIME 2024–202592.2 %independentEpoch AI Benchmarking Hub
2026-05-07

Agent + model results

systems, not bare-model scores
agent + model Epoch Inspect harness + GLM 5.1SWE-bench Verified74.2 %independentEpoch AI Benchmarking Hub
agent + model Artificial Analysis harness + GLM 5.1Terminal-Bench 2.161.8 %independentArtificial Analysis
agent + model Claude Code + GLM 5.1Terminal-Bench 2.158.6 %communityTerminal-Bench Leaderboard
agent + model Artificial Analysis harness + GLM 5.1Terminal-Bench Hard43.2 %independentArtificial Analysis
agent + model Artificial Analysis harness + GLM 5.1Terminal-Bench Hard35.6 %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 4.7GLM 4.6GLM 4.5GLM 4 6vGLM 4 5vGLM 4 0520