Comprehensive side-by-side LLM comparison
Both models show comparable benchmark performance. o1 mini offers 61.4K more tokens in context window than GPT-OSS-120B. o1 mini is $Infinity cheaper per million tokens. Both models have their strengths depending on your specific coding needs.
OpenAI
GPT-OSS-120B, released by OpenAI in August 2025, is an open-weight large language model with 120 billion parameters distributed under the Apache 2.0 license. It represents OpenAI's entry into the open-source model space, enabling developers to self-host and fine-tune a GPT-5-generation-class model. GPT-OSS-120B targets research applications, on-premises deployments, and custom fine-tuning workflows requiring a large open-weight base model.
OpenAI
OpenAI o1 mini, released by OpenAI in September 2024, is a lightweight reasoning model from the o1 family optimized for efficient STEM problem-solving at lower cost and latency. It features a 128K token context window and applies chain-of-thought reasoning specifically tuned for mathematics, science, and coding tasks. o1 mini targets use cases where rapid, cost-efficient reasoning is preferred over the broader capabilities of the full o1 model.
10 months newer

o1 mini
OpenAI
2024-09-12

GPT-OSS-120B
OpenAI
2025-08
Cost per million tokens (USD)
GPT-OSS-120B
o1 mini
Context window and performance specifications
Average performance across 1 common benchmarks
GPT-OSS-120B
o1 mini
Performance comparison across key benchmark categories
GPT-OSS-120B
o1 mini
Available providers and their performance metrics
GPT-OSS-120B
Hugging Face
o1 mini
GPT-OSS-120B
o1 mini
GPT-OSS-120B
o1 mini
OpenAI