Comprehensive side-by-side LLM comparison
GPT-OSS-120B leads with 22.2% higher average benchmark score. GPT-4o offers 12.3K more tokens in context window than GPT-OSS-120B. GPT-4o is $Infinity cheaper per million tokens. GPT-4o supports multimodal inputs. Overall, GPT-OSS-120B is the stronger choice for coding tasks.
OpenAI
GPT-4o, released by OpenAI in May 2024, is a multimodal large language model from the GPT-4 family that natively processes text, image, and audio inputs in a single end-to-end model. It features a 128K token context window and demonstrated competitive performance across coding, reasoning, and vision benchmarks at its release. GPT-4o targets general-purpose assistant applications, vision-enabled workflows, and use cases requiring low-latency multimodal understanding.
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.
1 year newer

GPT-4o
OpenAI
2024-05-13

GPT-OSS-120B
OpenAI
2025-08
Cost per million tokens (USD)
GPT-4o
GPT-OSS-120B
Context window and performance specifications
Average performance across 1 common benchmarks
GPT-4o
GPT-OSS-120B
Performance comparison across key benchmark categories
GPT-4o
GPT-OSS-120B
GPT-4o
2024-04
Available providers and their performance metrics
GPT-4o
OpenAI
GPT-OSS-120B
GPT-4o
GPT-OSS-120B
GPT-4o
GPT-OSS-120B
Hugging Face