BenchAtlas

Rankings / zai

GLM 4.7 Flash

open weights

released 2026-01-19

BenchAtlas Index

as of 2026-09-11
38.6
thinking
rank #314
7 families · 4 categories · medium
33.0
no reasoning
rank #359
8 families · 5 categories · high

Benchmark evidence

40 results
agentic coding
τ²-Benchthinking98.8 %independentArtificial Analysis
τ²-Benchno reasoning91.8 %independentArtificial Analysis
coding
SciCodethinking33.7 %independentArtificial Analysis
SciCodeno reasoning25.5 %independentArtificial Analysis
external indices
Intelligence Index v4.1thinking14.9 pointsindependentArtificial Analysis
Intelligence Index v4.1no reasoning10.6 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1425.3
1414.1–1436.5
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1422.9
1413.8–1432.0
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1419.4
1397.7–1441.1
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1399.9
1388.2–1411.5
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1392.0
1383.3–1400.7
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1390.2
1370.1–1410.2
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1385.5
1378.0–1392.9
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
1381.7
1367.9–1395.4
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1379.3
1359.3–1399.3
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1372.2
1361.8–1382.7
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
1370.7
1358.1–1383.2
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1368.0
1346.9–1389.0
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1366.5
1345.1–1387.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1366.4
1360.6–1372.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1361.9
1348.9–1374.9
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1348.7
1338.3–1359.1
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1347.8
1333.5–1362.0
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1343.5
1336.2–1350.8
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
1332.4
1320.6–1344.2
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1329.6
1320.9–1338.2
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
1319.5
1306.3–1332.6
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1305.8
1291.7–1319.9
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond60.5 %independentEpoch AI Benchmarking Hub
2026-08-30
GPQA Diamond
implementation=artificial-analysis
thinking58.1 %independentArtificial Analysis
GPQA Diamond
implementation=artificial-analysis
no reasoning45.2 %independentArtificial Analysis
GPQA Diamondno reasoning45.1 %independentEpoch AI Benchmarking Hub
2026-08-30
Humanity's Last Exam
implementation=artificial-analysis
thinking7.6 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
no reasoning5.0 %independentArtificial Analysis
long context instruction
AA-LCRthinking41.7 %independentArtificial Analysis
AA-LCRno reasoning20.3 %independentArtificial Analysis
IFBenchthinking60.8 %independentArtificial Analysis
IFBenchno reasoning46.3 %independentArtificial Analysis
reasoning math
OTIS Mock AIME 2024–202558.3 %independentEpoch AI Benchmarking Hub
2026-08-30
OTIS Mock AIME 2024–2025no reasoning25.0 %independentEpoch AI Benchmarking Hub
2026-08-28

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + GLM 4.7 FlashTerminal-Bench Hard22.0 %independentArtificial Analysis
agent + model Artificial Analysis harness + GLM 4.7 FlashTerminal-Bench Hard3.8 %independentArtificial Analysis

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