PipelineScore
← Back to leaderboard
Head-to-head

gemma4:31b-it-q4_K_M vs gpt-oss:latest

gpt-oss:latest wins+91.6 ptson the balanced composite.
local
Winner
gpt-oss:latest
91.6TRUNK

Category-by-category

Higher bar wins each row.

gemma4:31b-it-q4_K_M
Category
gpt-oss:latest
-100.00.0
Code
100.0+100.0
-80.00.0
Reason
80.0+80.0
-87.50.0
Tool Use
87.5+87.5
-100.00.0
RAG
100.0+100.0
-88.10.0
Speed
88.1+88.1
gemma4:31b-it-q4_K_M
Provider
local
Released
Context
0K
Lab
Community
gpt-oss:latest
Provider
local
Released
Context
0K
Lab
Community