The AI arena is free today

Open Superagent

Gemma 3n E2B Instructed vs GPT OSS 20B

GPT OSS 20B leads the LLM Stats Score 18.0 to -10.6.

Google · OpenAI · Updated for 2026

Which is better?

GPT OSS 20B leads the overall LLM Stats Score 18.0 to -10.6, ranking #219 overall.

In the 2 individual benchmarks reported for both models, GPT OSS 20B wins 2; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Gemma 3n E2B Instructed

  • you are already invested in the Google ecosystem

Choose GPT OSS 20B

  • overall performance matters — it scores 18.0 and ranks #219 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Aug 2025
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Gemma 3n E2B Instructed
Google
GPT OSS 20B
OpenAI
Core performance indexes
LLM Stats Score
-10.6
#371
18.0
#219
Reasoning
-11.0
#363
15.6
#225
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
— / M
$0.03 / M
Output price
— / M
$0.14 / M
Context window
—
131,072

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 3n E2B Instructed
GPT OSS 20B
Math
-8.0#324
17.0#199
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

18 reported for Gemma 3n E2B Instructed · 7 for GPT OSS 20B

2 shared

Gemma 3n E2B Instructed outperforms in 0 benchmarks, while GPT OSS 20B is better at 2 benchmarks (GPQA, MMLU).

GPT OSS 20B significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

12.9B diff

GPT OSS 20B has 12.9B more parameters than Gemma 3n E2B Instructed, making it 161.3% larger.

Google
Gemma 3n E2B Instructed
8.0Bparameters
OpenAI
GPT OSS 20B
20.9Bparameters
8.0B
Gemma 3n E2B Instructed
20.9B
GPT OSS 20B

Context Window

Maximum input and output token capacity

Only GPT OSS 20B specifies input context (131,072 tokens). Only GPT OSS 20B specifies output context (131,072 tokens).

Google
Gemma 3n E2B Instructed
Input- tokens
Output- tokens
OpenAI
GPT OSS 20B
Input131,072 tokens
Output131,072 tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemma 3n E2B Instructed supports multimodal inputs, whereas GPT OSS 20B does not.

Gemma 3n E2B Instructed can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 3n E2B Instructed

Text
Images
Audio
Video

GPT OSS 20B

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3n E2B Instructed is licensed under a proprietary license, while GPT OSS 20B uses Apache 2.0.

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

Gemma 3n E2B Instructed

Proprietary

Closed source

GPT OSS 20B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemma 3n E2B Instructed was released on 2025-06-26, while GPT OSS 20B was released on 2025-08-05.

GPT OSS 20B is 1 month newer than Gemma 3n E2B Instructed.

Gemma 3n E2B Instructed

Jun 26, 2025

1.2 years ago

GPT OSS 20B

Aug 5, 2025

1.1 years ago

1mo newer

Knowledge Cutoff

When training data ends

Gemma 3n E2B Instructed has a documented knowledge cutoff of 2024-06-01, while GPT OSS 20B's cutoff date is not specified.

We can confirm Gemma 3n E2B Instructed's training data extends to 2024-06-01, but cannot make a direct comparison without GPT OSS 20B's cutoff date.

Gemma 3n E2B Instructed

Jun 2024

GPT OSS 20B

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Gemma 3n E2B Instructed and GPT OSS 20B side-by-side, then vote on the output you prefer.

Gemma 3n E2B Instructed
✓ Preferred
GPT OSS 20B
Open in Playground

FAQ

Common questions about Gemma 3n E2B Instructed vs GPT OSS 20B.

Which is better, Gemma 3n E2B Instructed or GPT OSS 20B?

GPT OSS 20B leads the LLM Stats Score 18.0 to -10.6. Gemma 3n E2B Instructed is made by Google and GPT OSS 20B is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemma 3n E2B Instructed compare to GPT OSS 20B in benchmarks?

Gemma 3n E2B Instructed scores HumanEval: 66.5%, MMLU: 60.1%, Global-MMLU-Lite: 59.0%, MBPP: 56.6%, Global-MMLU: 55.1%. GPT OSS 20B scores MMLU: 85.3%, CodeForces: 74.3%, GPQA: 71.5%, TAU-bench Retail: 54.8%, HealthBench: 42.5%.

What are the context window sizes for Gemma 3n E2B Instructed and GPT OSS 20B?

Gemma 3n E2B Instructed supports an unknown number of tokens and GPT OSS 20B 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 Gemma 3n E2B Instructed and GPT OSS 20B?

Key differences include LLM Stats Score (-10.6 vs 18.0), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 3n E2B Instructed and GPT OSS 20B?

Gemma 3n E2B Instructed is developed by Google and GPT OSS 20B is developed by OpenAI.

Related comparisons