← Back to leaderboard
Head-to-head
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp vs openai/gpt-oss-20b
openai/gpt-oss-20b wins+7.6 pts (+9%)on the balanced composite.
Category-by-category
Higher bar wins each row.
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp
Category
openai/gpt-oss-20b
-12.587.5
Code
100.0+12.5
+15.090.0
Reason
75.0-15.0
87.5
Tool Use
87.5
100.0
RAG
100.0
-49.949.3
Speed
99.3+49.9
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community
openai/gpt-oss-20b
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community