← Back to leaderboard
Head-to-head
Qwen 2.5 32B Instruct vs openai/gpt-oss-20b
openai/gpt-oss-20b wins+15.9 pts (+21%)on the balanced composite.
Category-by-category
Higher bar wins each row.
Qwen 2.5 32B Instruct
Category
openai/gpt-oss-20b
-22.577.5
Code
100.0+22.5
+1.876.8
Reason
75.0-1.8
-12.375.2
Tool Use
87.5+12.3
-19.380.7
RAG
100.0+19.3
-28.870.5
Speed
99.3+28.8
Qwen 2.5 32B Instruct
- Provider
- alibaba
- Released
- 2024-09-19
- Context
- 131.072K
- Lab
- Community
openai/gpt-oss-20b
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community