← Back to leaderboard
Head-to-head
Dolphin 3.0 Llama 3.1 8B vs DeepSeek R1 671B-A37B
DeepSeek R1 671B-A37B wins+21.2 pts (+33%)on the balanced composite.
Category-by-category
Higher bar wins each row.
Dolphin 3.0 Llama 3.1 8B
Category
DeepSeek R1 671B-A37B
-18.968.6
Code
87.5+18.9
-19.163.5
Reason
82.7+19.1
-25.764.6
Tool Use
90.3+25.7
-19.163.8
RAG
82.9+19.1
-23.864.0
Speed
87.8+23.8
Dolphin 3.0 Llama 3.1 8B
- Provider
- cognitivecomputations
- Released
- 2025-01-04
- Context
- 131.072K
- Lab
- Community
DeepSeek R1 671B-A37B
- Provider
- deepseek
- Released
- 2025-01-20
- Context
- 128K
- Lab
- Community