The Model Index
Up to four models

GLM-5.1 vs GLM-5

On the index (GPT-4 = 100), GLM-5.1 scores 151 and GLM-5 142. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

GLM-5.1GLM-5
Next to GLM-5.1
Presets
GLM-5.1
151134–167
WeightsOpen
ReleasedApr 2026
Price in / out$1.4 / $4.4
Context205K
Core tests taken5 of 9
GLM-5
142126–157
WeightsOpen
ReleasedFeb 2026
Price in / out$1.0 / $3.2
Context205K
Core tests taken3 of 9

GLM-5.1 leads GLM-5 by 9 points, ahead on 2 of 2 shared core tests, at 1.4× the price.

Test by testthird-party results

GLM-5.1GLM-5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProSimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGSWE-bench VerifiedSWE-bench VerifiedLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchTaxEval v2TaxEval v2
Every result as a table
TestGLM-5.1GLM-5
Reasoning & knowledge
GPQA Diamond (Epoch AI)89.9%87.8%
GPQA Diamond (Vals AI)84.5%83.3%
MMLU Pro86.9%86.0%
SimpleBench55.1%53.2%
Maths
AIME-style maths (OTIS mock)93.3%80.0%
FrontierMath (2025 set)33.5%16.4%
FrontierMath tier 4 (2025 set)12.5%2.1%
Coding
SWE-bench Verified74.2%72.1%
LiveCodeBench81.4%81.9%
SWE-bench76.4%71.4%
Vibe Code Bench v1.131.5%23.4%
WeirdML57.1%48.2%
Professional work
CorpFin v264.5%62.9%
LegalBench84.4%84.1%
TaxEval v271.2%70.0%

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

This page as a chartDownload PNG