gpt-oss-120b vs gemini-3.8-flash
Both run on onomeo with free credits. Everything below comes from calls made through this site.
- gpt-oss-120b
- 6 advantages
- gemini-3.8-flash
- 3 advantages
How to choose
gpt-oss-120bSteadier: 100% up over 3 daysSteadier this week: 100% of tests passedFaster: 1.3s on averageHigher in this week's ranking: #2No training on conversationsOpen weights
gemini-3.8-flashCheaper: about 295 a reply, 55% lessLonger context: 1M tokensReads images
gpt-oss-120b
By OpenAI
gemini-3.8-flash
By GoogleNew this week
Where they differ
gpt-oss-120bgemini-3.8-flash
On this site
100%66 callsAvailability, last 3 days18%16 calls
100%83 testsAvailability, this week's tests25%20 tests
1.3sAverage response this week5.6s
652Credits per reply295
#2Place in this week's ranking#36
The model itself
128K tokensContext length1M tokens
32K tokensLongest reply64K tokens
NoReads imagesYes
Not used for training.Conversations used for trainingUsed to train and improve the provider’s models.
Jun 2024Knowledge cutoffNot published
5 Aug 2025Released2 Sep 2026
YesOpen weightsNo
Where they match
- Replies a day's check-in buys~288
- Calls toolsYes
- Thinks before answeringYes
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 Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.