PipelineScore
← Back to leaderboard
Head-to-head

openai/gpt-oss-20b vs qwen3-coder:30b

openai/gpt-oss-20b wins+5.5 pts (+6%)on the balanced composite.
local
Winner
openai/gpt-oss-20b
92.0TRUNK
local
qwen3-coder:30b
86.6MAINLINE

Category-by-category

Higher bar wins each row.

openai/gpt-oss-20b
Category
qwen3-coder:30b
100.0
Code
100.0
+5.075.0
Reason
70.0-5.0
-12.587.5
Tool Use
100.0+12.5
100.0
RAG
100.0
+44.799.3
Speed
54.5-44.7
openai/gpt-oss-20b
Provider
local
Released
Context
0K
Lab
Community
qwen3-coder:30b
Provider
local
Released
Context
0K
Lab
Community