The AI arena is free today

Open Superagent

GPT-5.1 Medium vs GPT OSS 20B High

GPT OSS 20B High significantly outperforms across most benchmarks. GPT OSS 20B High is 17.2x cheaper per token.

OpenAI · OpenAI · Updated for 2026

Which is better?

GPT-5.1 Medium outperforms in 0 benchmarks, while GPT OSS 20B High is better at 1 benchmark (AIME 2025). GPT OSS 20B High significantly outperforms across most benchmarks.

On price, GPT OSS 20B High is roughly 17.2x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-5.1 Medium also accepts a larger context window (400,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current benchmark, pricing, and model metadata for 2026.

Choose GPT-5.1 Medium

  • you process long inputs — it offers a 400,000 token context window
  • you want the most recent training data — it shipped Nov 2025

Choose GPT OSS 20B High

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • cost matters — it's about 17.2x cheaper per token
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Benchmark wins
0 of 1
1 of 1
Input price
$1.25 / M
$0.10 / M
Output price
$10.00 / M
$0.50 / M
Context window
400,000
131,072
Released
Nov 2025
Aug 2025
License
Proprietary
Apache 2.0

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

GPT-5.1 Medium outperforms in 0 benchmarks, while GPT OSS 20B High is better at 1 benchmark (AIME 2025).

GPT OSS 20B High significantly outperforms across most benchmarks.

Mon Aug 24 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Pricing Analysis

Price comparison per million tokens

GPT OSS 20B High costs less

For input processing, GPT-5.1 Medium ($1.25/1M tokens) is 12.5x more expensive than GPT OSS 20B High ($0.10/1M tokens).

For output processing, GPT-5.1 Medium ($10.00/1M tokens) is 20.0x more expensive than GPT OSS 20B High ($0.50/1M tokens).

In conclusion, GPT-5.1 Medium is more expensive than GPT OSS 20B High.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Mon Aug 24 2026 • llm-stats.com
OpenAI
GPT-5.1 Medium
Input tokens$1.25
Output tokens$10.00
Best providerOpenAI
OpenAI
GPT OSS 20B High
Input tokens$0.10
Output tokens$0.50
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-5.1 Medium accepts 400,000 input tokens compared to GPT OSS 20B High's 131,072 tokens. GPT OSS 20B High can generate longer responses up to 131,072 tokens, while GPT-5.1 Medium is limited to 128,000 tokens.

OpenAI
GPT-5.1 Medium
Input400,000 tokens
Output128,000 tokens
OpenAI
GPT OSS 20B High
Input131,072 tokens
Output131,072 tokens
Mon Aug 24 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

GPT-5.1 Medium supports multimodal inputs, whereas GPT OSS 20B High does not.

GPT-5.1 Medium can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5.1 Medium

Text
Images
Audio
Video

GPT OSS 20B High

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-5.1 Medium is licensed under a proprietary license, while GPT OSS 20B High uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

GPT-5.1 Medium

Proprietary

Closed source

GPT OSS 20B High

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-5.1 Medium was released on 2025-11-12, while GPT OSS 20B High was released on 2025-08-05.

GPT-5.1 Medium is 3 months newer than GPT OSS 20B High.

GPT-5.1 Medium

Nov 12, 2025

9 months ago

3mo newer
GPT OSS 20B High

Aug 5, 2025

1.1 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

GPT-5.1 Medium is available from OpenAI. GPT OSS 20B High is available from OpenAI.

GPT-5.1 Medium

openai logo
OpenAI
Input Price:Input: $1.25/1MOutput Price:Output: $10.00/1M

GPT OSS 20B High

openai logo
OpenAI
Input Price:Input: $0.10/1MOutput Price:Output: $0.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-5.1 Medium and GPT OSS 20B High side-by-side, then vote on the output you prefer.

GPT-5.1 Medium
✓ Preferred
GPT OSS 20B High
Open in Playground

FAQ

Common questions about GPT-5.1 Medium vs GPT OSS 20B High.

Which is better, GPT-5.1 Medium or GPT OSS 20B High?

GPT OSS 20B High significantly outperforms across most benchmarks. GPT-5.1 Medium is made by OpenAI and GPT OSS 20B High is made by OpenAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does GPT-5.1 Medium compare to GPT OSS 20B High in benchmarks?

GPT-5.1 Medium scores AIME 2025: 98.4%. GPT OSS 20B High scores AIME 2025: 98.7%, GPQA: 74.2%.

Is GPT-5.1 Medium cheaper than GPT OSS 20B High?

GPT OSS 20B High is 12.5x cheaper for input tokens. GPT-5.1 Medium costs $1.25/M input and $10.00/M output via openai. GPT OSS 20B High costs $0.10/M input and $0.50/M output via openai.

What are the context window sizes for GPT-5.1 Medium and GPT OSS 20B High?

GPT-5.1 Medium supports 400K tokens and GPT OSS 20B High supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5.1 Medium and GPT OSS 20B High?

Key differences include context window (400K vs 131K), input pricing ($1.25 vs $0.10/M), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.