gpt-oss-120bvsQwen3

gpt-oss-120b
Qwen3
Specifications
Parameters
117B
235B
Context window
128k
128k
Benchmarks
Nonsense detection
BullshitBench v2
11%
Coding
SWE-Bench Verified
62.4%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
14.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
19%
Science
GPQA Diamond
80.1%
General knowledge
MMLU
90%
Overview
CompanyOpenAIQwen
Release dateAug 5 2025Apr 29 2025
AccessOpen WeightOpen Weight

Which is better: gpt-oss-120b or Qwen3?

gpt-oss-120b and Qwen3 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen3 shipped 98 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

gpt-oss-120b has 117B parameters, while Qwen3 has 235B. Context windows are 128k (gpt-oss-120b) vs 128k (Qwen3).

Direct benchmark comparisons are unavailable — gpt-oss-120b and Qwen3 don't publish scores on any of the same benchmarks.

Frequently asked questions

gpt-oss-120b was released by OpenAI on Aug 5 2025.

Qwen3 was released by Qwen on Apr 29 2025.

gpt-oss-120b has a 128k context window; Qwen3 has 128k.

Other comparisons