Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
Open LLM Leaderboard
Report a problem with this record
anchor
Findings
IC-869
Models ranking highly on popular LLM leaderboards perform worse than Llama-2-70b-chat on Skill-Mix, suggesting cramming for the leaderboard at the expense of general-purpose text generation
[compared-to]
IC-869
Models ranking highly on popular LLM leaderboards perform worse than Llama-2-70b-chat on Skill-Mix, suggesting cramming for the leaderboard at the expense of general-purpose text generation
[eval]