PipelineScore
← Back to leaderboard
Head-to-head

Dolphin 3.0 Llama 3.1 8B vs DeepSeek Coder V2 236B

DeepSeek Coder V2 236B wins+19.9 pts (+31%)on the balanced composite.
cognitivecomputations
Dolphin 3.0 Llama 3.1 8B
65.1FEEDER
deepseek
Winner
DeepSeek Coder V2 236B
85.0MAINLINE

Category-by-category

Higher bar wins each row.

Dolphin 3.0 Llama 3.1 8B
Category
DeepSeek Coder V2 236B
-18.668.6
Code
87.2+18.6
-20.263.5
Reason
83.7+20.2
-20.364.6
Tool Use
84.8+20.3
-25.363.8
RAG
89.0+25.3
-24.764.0
Speed
88.7+24.7
Dolphin 3.0 Llama 3.1 8B
Provider
cognitivecomputations
Released
2025-01-04
Context
131.072K
Lab
Community
DeepSeek Coder V2 236B
Provider
deepseek
Released
2024-06-17
Context
163.84K
Lab
Community
Dolphin 3.0 Llama 3.1 8B vs DeepSeek Coder V2 236B · PipelineScore