gpt-oss-20bvsQwen2.5-Max

gpt-oss-20b
Qwen2.5-Max
Specifications
Parameters
21B
Context window
128k
32k
Benchmarks
Coding
SWE-Bench Verified
60.7%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
10.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
17.3%
Science
GPQA Diamond
71.5%
General knowledge
MMLU
85.3%
Overview
CompanyOpenAIQwen
Release dateAug 5 2025Jan 28 2025
AccessOpen WeightProprietary

Which is better: gpt-oss-20b or Qwen2.5-Max?

gpt-oss-20b and Qwen2.5-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Max shipped 189 days before gpt-oss-20b, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (gpt-oss-20b) vs 32k (Qwen2.5-Max). gpt-oss-20b is open weight, while Qwen2.5-Max is proprietary.

Direct benchmark comparisons are unavailable — gpt-oss-20b and Qwen2.5-Max don't publish scores on any of the same benchmarks.

Frequently asked questions

gpt-oss-20b was released by OpenAI on Aug 5 2025.

Qwen2.5-Max was released by Qwen on Jan 28 2025.

gpt-oss-20b has a 128k context window; Qwen2.5-Max has 32k.

gpt-oss-20b is an open weight model released by OpenAI. Qwen2.5-Max is a proprietary model released by Qwen.

Other comparisons