← Back to leaderboard
Head-to-head
swift-1.5-qwen3.8-27b-gsq-rco vs openai/gpt-oss-20b
openai/gpt-oss-20b wins+9.7 pts (+12%)on the balanced composite.
Category-by-category
Higher bar wins each row.
swift-1.5-qwen3.8-27b-gsq-rco
Category
openai/gpt-oss-20b
100.0
Code
100.0
+15.090.0
Reason
75.0-15.0
87.5
Tool Use
87.5
100.0
RAG
100.0
-87.511.7
Speed
99.3+87.5
swift-1.5-qwen3.8-27b-gsq-rco
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community
openai/gpt-oss-20b
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community