PipelineScore
← Back to leaderboard
Head-to-head

Dolphin 3.0 Llama 3.1 8B vs DeepSeek V3 671B-A37B

DeepSeek V3 671B-A37B wins+16.9 pts (+26%)on the balanced composite.
cognitivecomputations
Dolphin 3.0 Llama 3.1 8B
65.1FEEDER
deepseek
Winner
DeepSeek V3 671B-A37B
82.0MAINLINE

Category-by-category

Higher bar wins each row.

Dolphin 3.0 Llama 3.1 8B
Category
DeepSeek V3 671B-A37B
-12.768.6
Code
81.3+12.7
-18.763.5
Reason
82.3+18.7
-19.764.6
Tool Use
84.3+19.7
-21.363.8
RAG
85.1+21.3
-15.764.0
Speed
79.7+15.7
Dolphin 3.0 Llama 3.1 8B
Provider
cognitivecomputations
Released
2025-01-04
Context
131.072K
Lab
Community
DeepSeek V3 671B-A37B
Provider
deepseek
Released
2024-12-26
Context
128K
Lab
Community