GLM

GLM 4.5

GLM / Z.ai

36scores
35benchmarks
$0.6 / $2.2 per 1M tokenscost in/out

Metadata

GLM Open source

Aliases: glm-4.5, z-ai-glm-4.5, z-ai/glm-4.5

Benchmark Results

Benchmark Category Rank Score Sampled
MCP-Universe Agentic 13 24.68 2026-05-06
MCPMark Agentic 30 0.16 2026-05-06
Tau2-Bench Telecom Agentic 198 43% 2026-05-11
Terminal-Bench Hard Agentic 135 22% 2026-05-11
OpenUGI Alignment 19 58.64 2026-05-06
OpenUGI Alignment 496 36.81 2026-05-06
ALE-Bench Coding 76 344.82 2026-05-06
IOI Coding 46 2.917% 2026-05-26
LiveCodeBench Coding 67 67.446% 2026-05-28
SciCode Coding 195 34.8% 2026-05-11
NeoEvalPlusN Creative 9 19 2026-05-06
AI Energy Score Efficiency 196 1 2026-05-06
CorpFin v2 Finance 41 60.956% 2026-05-28
TaxEval v2 Finance 42 72.404% 2026-05-28
BenchLM General Knowledge 93 27 2026-05-06
MedQA Healthcare 50 89.975% 2026-04-16
Artificial Analysis Intelligence Index Intelligence 178 26.42 2026-05-11
GPQA Diamond Intelligence 63 72.222% 2026-05-28
Humanity's Last Exam Intelligence 123 12.2% 2026-05-11
MMLU Pro Intelligence 55 81.222% 2026-05-28
MMLU-Pro Intelligence 55 83.5% 2026-05-11
LegalBench Legal 79 75.627% 2026-05-28
ConStory-Bench Long Context 10 CED 0.595 2026-05-28
AIME Math 31 86.667% 2026-04-16
AIME 2025 Math 83 73.7% 2026-05-11
MATH 500 Math 14 94% 2026-01-09
MGSM Math 37 90.836% 2026-01-09
MATH-500 Mathematics 3 0.98 2026-05-06
LiveMedBench Medical 7 0.2246 2026-05-27
Design Arena Multimodal 49 1224 2026-05-06
Artificial Analysis Openness Index Openness 27 55.56 2026-05-11
GPQA Diamond Reasoning 120 78.2% 2026-05-11
Humanity's Last Exam (Text Only) Reasoning 29 9.64 2026-05-06
MultiNRC Reasoning 31 17.44 2026-05-06
CritPt Science 202 0% 2026-05-11
BFCL-v3 Tool Use 1 0.78 2026-05-06