GLM

GLM 5

GLM / Z.ai

74scores
65benchmarks
$0.6 / $2.08 per 1M tokenscost in/out

Metadata

GLM Open source

Aliases: glm-5, glm-5-20260211, z-ai-glm-5, z-ai-glm-5-20260211, z-ai/glm-5, z-ai/glm-5-20260211

Benchmark Results

Benchmark Category Rank Score Sampled
APEX-Agents Agentic 21 30.80 2026-05-06
APEX-Agents-AA Agentic 11 14.5% 2026-05-11
APEX-v1-extended Agentic 2 49 2026-05-06
ARC-AGI-1 Agentic 70 44.67 2026-05-05
ARC-AGI-2 Agentic 69 4.86 2026-05-05
AutoLab Agentic 4 0.60 2026-05-06
Claw-Eval-Live Agentic 4 61.9 2026-05-27
EnterpriseOps-Gym Agentic 15 22.2% 2026-05-05
Gert Labs Rankings Agentic 26 0.49 2026-05-11
PinchBench Agentic 20 0.86 2026-05-06
RuneBench Agentic 15 1.90 2026-05-05
t2-bench Agentic 3 0.90 2026-05-06
Tau2-Bench Telecom Agentic 4 98.2% 2026-05-11
Tau2-Bench Telecom Agentic 8 97.4% 2026-05-11
Terminal-Bench Hard Agentic 25 43.2% 2026-05-11
Terminal-Bench Hard Agentic 39 39.4% 2026-05-11
Vending-Bench 2 Agentic 15 4432.12 2026-05-28
WildClawBench Agentic 3 42.60 2026-05-06
YC-Bench Agentic 2 1208190 2026-05-06
OpenUGI Alignment 43 54.56 2026-05-06
OpenUGI Alignment 628 33.71 2026-05-06
ALE-Bench Coding 46 765.63 2026-05-06
Arena AI Code Coding 23 1436 2026-05-06
IOI Coding 12 22% 2026-05-26
LiveCodeBench Coding 36 81.868% 2026-05-28
LMArena WebDev Arena Coding 23 1435.92 2026-05-06
SciCode Coding 36 46.2% 2026-05-11
SciCode Coding 132 38.3% 2026-05-11
SWE Atlas - Codebase QnA Coding 7 20.50 2026-05-06
SWE Atlas - Refactoring Coding 8 24.24 2026-05-06
SWE Atlas - Test Writing Coding 2 28.74 2026-05-06
SWE-bench Verified Coding 27 71.4% 2026-05-28
Terminal-Bench 2.0 Coding 21 49.438% 2026-05-28
TuRTLe Code Completion (Icarus Verilog) Coding 1 83.98 2026-05-06
TuRTLe Code Completion (Verilator) Coding 1 82.23 2026-05-06
TuRTLe Spec-to-RTL (Icarus Verilog) Coding 3 79.46 2026-05-06
TuRTLe Spec-to-RTL (Verilator) Coding 3 78.17 2026-05-06
Vibe Code Bench v1.1 Coding 20 23.359% 2026-05-28
OrgForge-IT Cybersecurity 6 0.800 2026-05-28
SecCodeBench Cybersecurity 5 62.13% 2026-05-28
Vectara HHEM Hallucination Leaderboard Factuality 55 89.90 2026-05-06
CorpFin v2 Finance 29 62.898% 2026-05-28
Finance Agent v1.1 Finance 21 53.182% 2026-05-04
TaxEval v2 Finance 67 70.033% 2026-05-28
React Native Evals Frontend Development 12 74.8352% overall 2026-05-28
ALL Bench LLM General Knowledge 7 48.85 2026-05-06
BenchLM General Knowledge 17 82 2026-05-06
BenchLM General Knowledge 35 67 2026-05-06
MedQA Healthcare 18 94.267% 2026-04-16
AIIQ Composite IQ Intelligence 19 113 2026-05-12
Artificial Analysis Intelligence Index Intelligence 22 49.77 2026-05-11
Artificial Analysis Intelligence Index Intelligence 73 40.57 2026-05-11
GPQA Diamond Intelligence 31 83.333% 2026-05-28
Humanity's Last Exam Intelligence 36 27.2% 2026-05-11
Humanity's Last Exam Intelligence 205 7.2% 2026-05-11
LiveBench Intelligence 36 68.70 2026-05-05
MMLU Pro Intelligence 29 86.03% 2026-05-28
AraGen v3 Language 27 46.01 2026-05-06
CaseLaw v2 Legal 45 52.519% 2026-05-04
LegalBench Legal 21 84.059% 2026-05-28
AIME Math 23 91.667% 2026-04-16
AIME 2026 Mathematics 3 95.83 2026-05-06
HMMT February 2026 Mathematics 4 86.36 2026-05-06
ALL Bench Multimodal Multimodal 6 44.06 2026-05-06
Design Arena Multimodal 12 1308 2026-05-06
Artificial Analysis Openness Index Openness 55 50 2026-05-11
Altered Riddles Reasoning 8 0.3460 2026-05-27
FINAL Bench Metacognitive Reasoning 4 76.38 2026-05-06
GPQA Diamond Reasoning 86 82% 2026-05-11
GPQA Diamond Reasoning 235 66.6% 2026-05-11
InvisibleBench Safety 5 0.05 2026-05-06
LiveSecBench Safety 18 56.73 2026-05-27
CritPt Science 59 2% 2026-05-11
CritPt Science 211 0% 2026-05-11