artifact
active
artifact:claude-4-1-opusClaude 4.1 Opus
LLM judge and explainer used throughout.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (5)
method
- Transfer-based 1-5 score via model stitching and LLM judge; 6 minus similarity.
- Claude judge rating exceptionalism, factuality, coherence on 30 prompts.
- Claude judge rating Chinese alignment and coherence on 30 prompts.
- Evaluations on copyrighted and harmless prompts for GPT-OSS feature.
- Tracks GPT/ChatGPT mentions under steering.
Institutes (1)
institute
- Anthropicassociated_withLab behind Claude models and Constitutional AI training approach; represents highest baseline scores and lowest prompt lift.