gpt-oss-20bvsQwen3.7-Max

gpt-oss-20b
Qwen3.7-Max
Specifications
Parameters
21B
Context window
128k
Benchmarks
Nonsense detection
BullshitBench v2
71%
Agentic coding
SWE-Bench Pro
60.6%
Coding
SWE-Bench Verified
60.7%
Competitive coding
LiveCodeBench
91.6%
Agentic terminal coding
Terminal-Bench 2.0
69.7%
Multi-step tool use
MCP Atlas
76.4%
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%
92.4%Best
General knowledge
MMLU
85.3%
Community preference
Arena Elo (Text)
1475
Overview
CompanyOpenAIQwen
Release dateAug 5 2025May 20 2026
AccessOpen WeightProprietary

Which is better: gpt-oss-20b or Qwen3.7-Max?

Qwen3.7-Max leads gpt-oss-20b on 1 of the 1 benchmark they both report (GPQA Diamond). gpt-oss-20b shipped 288 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.

gpt-oss-20b is open weight, while Qwen3.7-Max is proprietary.

On GPQA Diamond, Qwen3.7-Max leads at 92.4% vs gpt-oss-20b at 71.5%.

Frequently asked questions

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

Qwen3.7-Max was released by Qwen on May 20 2026.

Qwen3.7-Max leads on GPQA Diamond — gpt-oss-20b 71.5% vs Qwen3.7-Max 92.4%.

gpt-oss-20b is an open weight model released by OpenAI. Qwen3.7-Max is a proprietary model released by Qwen.

Other comparisons