Model Comparison
GPT OSS 20B High vs Mercury 2Which is better in 2026?
GPT OSS 20B High significantly outperforms across most benchmarks. GPT OSS 20B High is 1.9x cheaper per token.
Verdict: GPT OSS 20B High vs Mercury 2 — which is better?
GPT OSS 20B High (by OpenAI) and Mercury 2 (by Inception) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
GPT OSS 20B High outperforms in 2 benchmarks (AIME 2025, GPQA), while Mercury 2 is better at 0 benchmarks. GPT OSS 20B High significantly outperforms across most benchmarks.
On price, GPT OSS 20B High is roughly 1.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
GPT OSS 20B High also accepts a larger context window (131,072 input tokens), making it the stronger choice for long documents and large codebases.
Choose GPT OSS 20B High if…
- you want the strongest raw capability — it leads on 2 of 2 shared benchmarks
- cost matters — it's about 1.9x cheaper per token
- you process long inputs — it offers a 131,072 token context window
- you need open weights you can self-host or fine-tune
Choose Mercury 2 if…
- you want the most recent training data — it shipped Feb 2026
Performance Benchmarks
Comparative analysis across standard metrics
GPT OSS 20B High outperforms in 2 benchmarks (AIME 2025, GPQA), while Mercury 2 is better at 0 benchmarks.
GPT OSS 20B High significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, GPT OSS 20B High ($0.10/1M tokens) is 2.5x cheaper than Mercury 2 ($0.25/1M tokens).
For output processing, GPT OSS 20B High ($0.50/1M tokens) is 1.5x cheaper than Mercury 2 ($0.75/1M tokens).
In conclusion, Mercury 2 is more expensive than GPT OSS 20B High.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
GPT OSS 20B High accepts 131,072 input tokens compared to Mercury 2's 128,000 tokens. GPT OSS 20B High can generate longer responses up to 131,072 tokens, while Mercury 2 is limited to 8,192 tokens.
License
Usage and distribution terms
GPT OSS 20B High is licensed under Apache 2.0, while Mercury 2 uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
Apache 2.0
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
GPT OSS 20B High was released on 2025-08-05, while Mercury 2 was released on 2026-02-24.
Mercury 2 is 7 months newer than GPT OSS 20B High.
Aug 5, 2025
1.0 years ago
Feb 24, 2026
5 months ago
6mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
GPT OSS 20B High is available from OpenAI. Mercury 2 is available from Inception.
GPT OSS 20B High
Mercury 2
Outputs Comparison
Key Takeaways
Mercury 2
View detailsInception
No standout differentiators in the data we have for this pair.
Detailed Comparison
Interactive Arena
Judge for yourself.
Run your own prompts against GPT OSS 20B High and Mercury 2 side-by-side, then vote on the output you prefer.
| Feature | | |
|---|
FAQ
Common questions about GPT OSS 20B High vs Mercury 2.