https://
artificialanalysis.ai/models/gpt-oss
-120b/providers#aime25x32-performance-gpt-oss-120b
…
GENERATIVE AI
-
GPT-OSS-120B Open Source Model Performance Analysis
By
–
-
GPT-5 Model Gains Recognition Despite Controversy
By
–
GPT-5 is an amazing model. I can’t believe that’s controversial.
-

Uncertainty About GPT-5-Thinking Development Work and Improvements
By
–
we still dont know if they did extra work (in the last 4 months since o3/o4mini release) on the reasoner they call gpt-5-thinking or if they just packed up the existing o4 they had lying around internally and shipped it the very slight improvements in benchmarks suggests the
-

GPT 120B Performance Analysis: AWS and Azure Implementation Issues
By
–
Artificial analysis team did great work analysing the performance of the OpenAI's GPT OSS 120b model across providers – AWS and Azure are lagging behind. I really did not appreciate the extend to which the performance can drop if the model is not implemented correctly
-

ChatGPT Gains Gmail Access: Exploring AI-Powered Email
By
–
Now ChatGPT has access to my Gmail, I can ask the important questions: And apparently @simonw
's newsletter is the funniest email I ever got! -

100M+ AI Characters with Unique Personalities
By
–
not just looks.. we've got personalities too (¬‿¬) here are 100M+ characters with peculiar personalities you can talk to http://
c.ai -

GPT-5 Exceeds Medical Professionals on Reasoning Benchmarks
By
–
GPT-4o was below the level of medical professionals on medical reasoning benchmarks GPT-5 (apparently Thinking medium) now far exceeds them. (Usual benchmark caveats apply)
-
Weekly Roundup of Major AI Model Releases and Breakthroughs
By
–
What a crazy week in AI.. – OpenAI's GPT-5 Launch
– Anthropic's Claude Opus 4.1 Release
– Google's Genie 3 World Simulator
– ElevenLabs Music Generation Model
– xAI's Grok Imagine with 'Spicy' Mode
– Alibaba’s Qwen-Image Model
– Tesla AI Breakthroughs for Robotaxi FSD
– -
Prompt Engineering Impact on Test Outcomes Analysis
By
–
The size of these impacts is much larger than the effect of most prompt engineering on test outcomes.