PipelineScore
← Back to leaderboard
Head-to-head

Dolphin 3.0 Llama 3.1 8B vs openai/gpt-oss-20b

openai/gpt-oss-20b wins+26.9 pts (+41%)on the balanced composite.
cognitivecomputations
Dolphin 3.0 Llama 3.1 8B
65.1FEEDER
local
Winner
openai/gpt-oss-20b
92.0TRUNK

Category-by-category

Higher bar wins each row.

Dolphin 3.0 Llama 3.1 8B
Category
openai/gpt-oss-20b
-31.468.6
Code
100.0+31.4
-11.563.5
Reason
75.0+11.5
-22.964.6
Tool Use
87.5+22.9
-36.263.8
RAG
100.0+36.2
-35.364.0
Speed
99.3+35.3
Dolphin 3.0 Llama 3.1 8B
Provider
cognitivecomputations
Released
2025-01-04
Context
131.072K
Lab
Community
openai/gpt-oss-20b
Provider
local
Released
Context
0K
Lab
Community