GPT-4 TurbovsGLM-5

GPT-4 Turbo
GLM-5
Specifications
Parameters
744B
Context window
128k
API pricing
Input price
$10.00$1.00
Output price
$30.00$3.20
Cached input price
$0.20
Cheapest input
$0.60DeepInfra
Cheapest output
$1.92GMICloud
Benchmarks
GPQA Diamond
42.5%86%
Benchmarks
BullshitBench v2
28%
SWE-Bench Verified
77.8%
SWE-Bench Multilingual
73.3%
Terminal-Bench 2.0
56.2%
BrowseComp
75.9%
Humanity's Last Exam · with tools
50.4%
Arena Elo (Code)
1435
Overview
CompanyOpenAIZ.ai
Release dateNov 6 2023Feb 12 2026
AccessProprietaryOpen Weight

Other comparisons

GPT-4 TurbovsClaude Opus 5GLM-5vsClaude Opus 5GPT-4 TurbovsGemini 3.7 FlashGLM-5vsGemini 3.7 FlashGPT-4 TurbovsMuse GlimmerGLM-5vsMuse GlimmerGPT-4 TurbovsGrok 4.6GLM-5vsGrok 4.6GPT-4 TurbovsDeepSeek-V4-Pro-0813GLM-5vsDeepSeek-V4-Pro-0813GPT-4 TurbovsMistral Medium 3.5GLM-5vsMistral Medium 3.5

Frequently asked questions

GLM-5 leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). GLM-5 is cheaper on both input and output: $1.00 vs $10.00 per million input tokens, and $3.20 vs $30.00 per million output tokens. GPT-4 Turbo shipped 829 days before GLM-5, so benchmark comparisons should account for the intervening progress.

GPT-4 Turbo is proprietary, while GLM-5 is open weight.

On GPQA Diamond, GLM-5 leads at 86% vs GPT-4 Turbo at 42.5%.

GPT-4 Turbo was released by OpenAI on Nov 6 2023.

GLM-5 was released by Z.ai on Feb 12 2026.

GLM-5 leads on GPQA Diamond — GPT-4 Turbo 42.5% vs GLM-5 86%.

GLM-5 is cheaper on both input and output: $1.00 vs $10.00 per million input tokens, and $3.20 vs $30.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.

GPT-4 Turbo is a proprietary model released by OpenAI. GLM-5 is an open weight model released by Z.ai.