GPT OSS 120B endpoints are not created equal.
In AIME25 math evals, Artificial Analysis found Cerebras was #1 in accuracy.
Cerebras Leads GPT OSS 120B in AIME25 Math Evaluations
By
–
By
–
GPT OSS 120B endpoints are not created equal.
In AIME25 math evals, Artificial Analysis found Cerebras was #1 in accuracy.