gpt-oss-120b vs glm-5.2
Both run on onomeo with free credits. Everything below comes from calls made through this site.
- gpt-oss-120b
- 4 advantages
- glm-5.2
- 1 advantage
How to choose
gpt-oss-120bCheaper: about 652 a reply, 73% lessFaster: 1.3s on averageHigher in this week's ranking: #2No training on conversations
glm-5.2Longer context: 1M tokens
gpt-oss-120b
By OpenAI
glm-5.2
By Zhipu AI
Where they differ
gpt-oss-120bglm-5.2
On this site
1.3sAverage response this week2.5s
652Credits per reply2,378
~288Replies a day's check-in buys~84
#2Place in this week's ranking#9
The model itself
128K tokensContext length1M tokens
32K tokensLongest reply128K tokens
Not used for training.Conversations used for trainingThe provider does not say.
Jun 2024Knowledge cutoffNot published
5 Aug 2025Released13 Jun 2026
Where they match
- Availability, last 3 days100%
- Availability, this week's tests100%
- Reads imagesNo
- Calls toolsYes
- Thinks before answeringYes
- Open weightsYes
Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Replies a day assumes a full daily check-in and the daily call limit.
Compare next
gpt-oss-120b against other models
Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.