GPT OSS 20B High vs Mistral Large 2: Specs & Benchmark Comparison
GPT OSS 20B High is developed by OpenAI, while Mistral Large 2 comes from Mistral AI. Mistral Large 2 was released in July 2024, and GPT OSS 20B High followed 15 months later in October 2025. Mistral Large 2 is the larger model at roughly 123 billion parameters, against 20 billion for GPT OSS 20B High.
We have 2 benchmark results for GPT OSS 20B High and 5 benchmark results for Mistral Large 2, but they were measured on different benchmarks, so there is no like-for-like scoreboard.
GPT OSS 20B High is the cheaper API at $0.10 per million input tokens and $0.50 per million output tokens, roughly 20 times cheaper than Mistral Large 2 at $2 and $6. Both accept a context window of about 128K tokens.
| Characteristic | GPT OSS 20B High | Mistral Large 2 |
|---|---|---|
| Company | OpenAI | Mistral AI |
| Release Date | October 1, 2025 | July 24, 2024 |
| Parameters | 20B | 123B |
| Multimodal | No | No |
| Context (input) | 131K | 128K |
| Context (output) | 131K | 128K |
| Input Price / 1M | $0.10 | $2.00 |
| Output Price / 1M | $0.50 | $6.00 |
| Average Score | 86.5% | 87.6% |
Verdict
GPT OSS 20B High leads in 3 out of 4 comparison categories.
Both models show comparable average scores: GPT OSS 20B High — 0.9, Mistral Large 2 — 0.9.
GPT OSS 20B High is 13.3x cheaper: input $0.10/1M vs $2.00/1M tokens.
GPT OSS 20B High supports a larger context: 131K vs 128K tokens.
GPT OSS 20B High is newer: released 10/1/2025 vs 7/24/2024.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GPT OSS 20B High or Mistral Large 2?
Which model is cheaper — GPT OSS 20B High or Mistral Large 2?
Which has a larger context window — GPT OSS 20B High or Mistral Large 2?
The GPT OSS 20B High and Mistral Large 2 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT OSS 20B High or Mistral Large 2 page. See also the complete list of AI model comparisons.