The Model Index
Up to four models

GLM-4.5 vs GLM-4.6

On the index (GPT-4 = 100), GLM-4.5 scores 132 and GLM-4.6 127. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GLM-4.5
Presets
GLM-4.5
132113–150
WeightsOpen
ReleasedJul 2025
Price in / out$0.60 / $2.2
Context131K
Core tests taken1 of 9
GLM-4.6
127108–145
WeightsOpen
ReleasedSep 2025
Price in / out$0.50 / $2.0
Context205K
Core tests taken0 of 9

GLM-4.5 and GLM-4.6 are too close to call (5 points apart, within the uncertainty), at a similar price.

Test by testthird-party results

GLM-4.5GLM-4.6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSMGSMMGSMCODINGLiveCodeBenchLiveCodeBenchPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchTaxEval v2TaxEval v2
Every result as a table
TestGLM-4.5GLM-4.6
Reasoning & knowledge
GPQA Diamond (Vals AI)72.2%74.5%
MMLU Pro81.2%82.2%
Maths
MGSM90.8%89.8%
Coding
LiveCodeBench67.5%81.0%
Professional work
CorpFin v261.0%56.8%
LegalBench75.6%79.6%
TaxEval v272.4%66.2%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG