gpt-oss-120bvsGLM-5

gpt-oss-120b
GLM-5
Specifications
Parameters
117B
744B
Context window
128k
Benchmarks
Nonsense detection
BullshitBench v2
11%
28%Best
Coding
SWE-Bench Verified
62.4%
77.8%Best
Multilingual coding
SWE-Bench Multilingual
73.3%
Agentic terminal coding
Terminal-Bench 2.0
56.2%
Web browsing
BrowseComp
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
14.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
19%
50.4%Best
Science
GPQA Diamond
80.1%
86%Best
General knowledge
MMLU
90%
Community preference (code)
Arena Elo (Code)
1435
Overview
CompanyOpenAIZ.ai
Release dateAug 5 2025Feb 12 2026
AccessOpen WeightOpen Weight

Which is better: gpt-oss-120b or GLM-5?

GLM-5 leads gpt-oss-120b on 4 of the 4 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond). gpt-oss-120b shipped 191 days before GLM-5, so benchmark comparisons should account for the intervening progress.

gpt-oss-120b has 117B parameters, while GLM-5 has 744B.

On BullshitBench v2, GLM-5 leads at 28% vs gpt-oss-120b at 11%. On SWE-Bench Verified, GLM-5 leads at 77.8% vs gpt-oss-120b at 62.4%. On Humanity's Last Exam · with tools, GLM-5 leads at 50.4% vs gpt-oss-120b at 19%. On GPQA Diamond, GLM-5 leads at 86% vs gpt-oss-120b at 80.1%.

Frequently asked questions

gpt-oss-120b was released by OpenAI on Aug 5 2025.

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

GLM-5 leads on SWE-Bench Verified — gpt-oss-120b 62.4% vs GLM-5 77.8%.

GLM-5 leads on Humanity's Last Exam · with tools — gpt-oss-120b 19% vs GLM-5 50.4%.

Other comparisons