Comprehensive side-by-side LLM comparison
o4 mini leads with 1.7% higher average benchmark score. o4 mini offers 167.9K more tokens in context window than GPT-OSS-120B. o4 mini is $Infinity cheaper per million tokens. o4 mini supports multimodal inputs. 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 o4 mini, released by OpenAI in April 2025, is a compact reasoning model from the o4 family that combines multimodal understanding with efficient chain-of-thought processing. It features a 200K token context window and native image understanding, with strong performance on mathematics and coding benchmarks relative to its inference cost. o4 mini targets cost-sensitive applications requiring both visual reasoning and mathematical accuracy.
3 months newer

o4 mini
OpenAI
2025-04-16

GPT-OSS-120B
OpenAI
2025-08
Cost per million tokens (USD)
GPT-OSS-120B
o4 mini
Context window and performance specifications
Average performance across 1 common benchmarks
GPT-OSS-120B
o4 mini
Performance comparison across key benchmark categories
GPT-OSS-120B
o4 mini
Available providers and their performance metrics
GPT-OSS-120B
Hugging Face
o4 mini
GPT-OSS-120B
o4 mini
GPT-OSS-120B
o4 mini
OpenAI