Comprehensive side-by-side LLM comparison
GPT-OSS-20B leads with 15.9% higher average benchmark score. GPT-4.1 mini offers 900.7K more tokens in context window than GPT-OSS-20B. GPT-4.1 mini is $Infinity cheaper per million tokens. GPT-4.1 mini supports multimodal inputs. Overall, GPT-OSS-20B is the stronger choice for coding tasks.
OpenAI
GPT-4.1 mini, released by OpenAI in April 2025, is a smaller variant from the GPT-4.1 family designed for efficient, cost-effective deployments requiring long-context understanding. It features a 1M token context window and native image understanding, with maintained coding and instruction-following capabilities relative to its size. GPT-4.1 mini targets applications needing a balance between response speed, cost, and capability, such as production APIs with high request volumes.
OpenAI
GPT-OSS-20B is an open-weight large language model with 20 billion parameters from OpenAI's open-source model initiative. It targets deployments requiring a smaller, efficient model that can run on consumer or mid-tier hardware while maintaining strong reasoning and coding capabilities relative to its size.
3 months newer

GPT-4.1 mini
OpenAI
2025-04-14

GPT-OSS-20B
OpenAI
2025-08-05
Cost per million tokens (USD)
GPT-4.1 mini
GPT-OSS-20B
Context window and performance specifications
Average performance across 1 common benchmarks
GPT-4.1 mini
GPT-OSS-20B
Performance comparison across key benchmark categories
GPT-4.1 mini
GPT-OSS-20B
Available providers and their performance metrics
GPT-4.1 mini
OpenAI
GPT-OSS-20B
GPT-4.1 mini
GPT-OSS-20B
GPT-4.1 mini
GPT-OSS-20B
Hugging Face