OpenAI: gpt-oss-20b Rank

gpt-oss-20b has an overall score of 59 out of 100, tied for rank 217 of 291. The published scores are price 99, context 44, parameters 33, and freshness 60. The overall score is their average. recency is not published and is left out of the average.

Data sourced from OpenRouter API and manual data collection | Last updated: Nov 3, 2026, 8:01 AM UTC

Overall score
59
Rank
217

tied for rank 217 of 291

Component scores

ScoreResultPublished valueSource
Freshness60AI Knowledge Cutoff
Recency——AI Release Date
Context44131K tokens, output 118KAI Context Window
Parameters3321B total, 3.6B activeAI Parameter Count
Price99$0.055 / 1M blended, $0.03 / 1M input, $0.13 / 1M outputAI Token Price

216 listed models have a higher overall score. Among OpenAI models, it ranks 36 of 49.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

All OpenAI modelsBest modelsHow the score is calculated

🤖 Generate website with AI 👆

Join the beta waitlist and get 50% off your first 3 months.

Join waitlist

Frequently asked questions

What is the gpt-oss-20b rank?

gpt-oss-20b has an overall score of 59 out of 100, tied for rank 217 of 291. The published scores are price 99, context 44, parameters 33, and freshness 60. The overall score is their average. recency is not published and is left out of the average.

Where does gpt-oss-20b rank?

gpt-oss-20b is tied for rank 217 of 291. 216 listed models have a higher overall score. Among OpenAI models, it ranks 36 of 49.

What scores make up gpt-oss-20b?

gpt-oss-20b scores price 99 (AI Token Price), context 44 (AI Context Window), parameters 33 (AI Parameter Count), and freshness 60 (AI Knowledge Cutoff). The overall score of 59 is the average of those 4.