← Back to leaderboard
Head-to-head
/home/thomaskyn/models/Qwen3.5-4b/Qwen3.5-4B-Q4_K_M.gguf vs openai/gpt-oss-20b
openai/gpt-oss-20b wins+34.2 pts (+59%)on the balanced composite.
Category-by-category
Higher bar wins each row.
/home/thomaskyn/models/Qwen3.5-4b/Qwen3.5-4B-Q4_K_M.gguf
Category
openai/gpt-oss-20b
-50.050.0
Code
100.0+50.0
-35.040.0
Reason
75.0+35.0
87.5
Tool Use
87.5
-12.587.5
RAG
100.0+12.5
-70.029.2
Speed
99.3+70.0
/home/thomaskyn/models/Qwen3.5-4b/Qwen3.5-4B-Q4_K_M.gguf
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community
openai/gpt-oss-20b
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community