← Back to leaderboard
Head-to-head
Llama 3.1 8B Instruct vs openai/gpt-oss-20b
openai/gpt-oss-20b wins+28.1 pts (+44%)on the balanced composite.
Category-by-category
Higher bar wins each row.
Llama 3.1 8B Instruct
Category
openai/gpt-oss-20b
-37.562.5
Code
100.0+37.5
-10.464.6
Reason
75.0+10.4
-23.663.9
Tool Use
87.5+23.6
-34.565.5
RAG
100.0+34.5
-35.963.4
Speed
99.3+35.9
Llama 3.1 8B Instruct
- Provider
- meta
- Released
- 2024-07-23
- Context
- 128K
- Lab
- Community
openai/gpt-oss-20b
- Provider
- local
- Released
- Context
- 0K
- Lab
- Community