The Model Index
Up to four models

GPT-5 vs GLM-4.6

On the index (GPT-4 = 100), GPT-5 scores 149 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.

GPT-5GLM-4.6
Next to GPT-5
Presets
GPT-5
149133–164
WeightsClosed
ReleasedAug 2025
Price in / out$1.25 / $10
Context400K
Core tests taken6 of 9
GLM-4.6
127108–145
WeightsOpen
ReleasedSep 2025
Price in / out$0.50 / $2.0
Context205K
Core tests taken0 of 9

GPT-5 leads GLM-4.6 by 22 points, at 3.9× the price.

Test by testthird-party results

GPT-5GLM-4.6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSMGSMMGSMFrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGSWE-bench Pro (public set)SWE-bench Pro (public set)Terminal-Bench 2.0 (Terminus 2 runs)Terminal-Bench 2.0 (Terminus 2 runs)LiveCodeBenchLiveCodeBenchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchTaxEval v2TaxEval v2
Every result as a table
TestGPT-5GLM-4.6
Reasoning & knowledge
GPQA Diamond (Vals AI)85.6%74.5%
MMLU Pro86.5%82.2%
Maths
MGSM92.8%89.8%
FrontierMath (2025 set)32.4%3.8%
FrontierMath tier 4 (2025 set)12.5%2.1%
Coding
SWE-bench Pro (public set)41.8%9.7%
Terminal-Bench 2.0 (Terminus 2 runs)35.2%24.5%
LiveCodeBench85.9%81.0%
Vibe Code Bench v1.120.1%3.1%
Professional work
CorpFin v261.1%56.8%
LegalBench86.0%79.6%
TaxEval v273.4%66.2%
Task length · METR42 sec

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

This page as a chartDownload PNG