← Back to leaderboard
Head-to-head
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp vs gpt-oss-20b-GGUF
gpt-oss-20b-GGUF wins+8.9 pts (+11%)on the balanced composite.
Category-by-category
Higher bar wins each row.
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp
Category
gpt-oss-20b-GGUF
-12.587.5
Code
100.0+12.5
+10.090.0
Reason
80.0-10.0
87.5
Tool Use
87.5
100.0
RAG
100.0
-50.749.3
Speed
100.0+50.7
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community
gpt-oss-20b-GGUF
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community