GPT-5.1 Medium vs GPT OSS 20B High: Specs & Benchmark Comparison
GPT-5.1 Medium and GPT OSS 20B High both come from OpenAI, GPT OSS 20B High was released in October 2025, and GPT-5.1 Medium followed a month later in November 2025. GPT OSS 20B High has a published size of about 20 billion parameters; OpenAI has not disclosed the parameter count of GPT-5.1 Medium.
We have 1 benchmark result for GPT-5.1 Medium and 2 benchmark results for GPT OSS 20B High, but they overlap on a single test: AIME 2025, where GPT OSS 20B High scores 98.7% against 98.0%.
GPT OSS 20B High is the cheaper API at $0.10 per million input tokens and $0.50 per million output tokens, roughly 13 times cheaper than GPT-5.1 Medium at $1.25 and $10. GPT-5.1 Medium takes the larger context window at 400K tokens, compared with 131K for GPT OSS 20B High. GPT-5.1 Medium accepts text and images as input, while GPT OSS 20B High accepts text.
| Characteristic | GPT-5.1 Medium | GPT OSS 20B High |
|---|---|---|
| Company | OpenAI | OpenAI |
| Release Date | November 11, 2025 | October 1, 2025 |
| Parameters | — | 20B |
| Multimodal | Yes | No |
| Context (input) | 400K | 131K |
| Context (output) | 128K | 131K |
| Input Price / 1M | $1.25 | $0.10 |
| Output Price / 1M | $10.00 | $0.50 |
| Average Score | 98.0% | 86.5% |
| Benchmarks | ||
| AIME 2025 | 98.0% | 98.7% |
Visual Benchmark Comparison
Verdict
GPT-5.1 Medium leads in 2 out of 4 comparison categories.
Both models show comparable average scores: GPT-5.1 Medium — 1.0, GPT OSS 20B High — 0.9.
GPT OSS 20B High is 18.8x cheaper: input $0.10/1M vs $1.25/1M tokens.
GPT-5.1 Medium supports a larger context: 400K vs 131K tokens.
GPT-5.1 Medium is newer: released 11/11/2025 vs 10/1/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GPT-5.1 Medium or GPT OSS 20B High?
Which model is cheaper — GPT-5.1 Medium or GPT OSS 20B High?
Which has a larger context window — GPT-5.1 Medium or GPT OSS 20B High?
The GPT-5.1 Medium and GPT OSS 20B High comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT-5.1 Medium or GPT OSS 20B High page. See also the complete list of AI model comparisons.