← swipe to navigate →
#357 ✓ stable
AI Industry
Do large language models degrade in accuracy when their own previous outputs are included in their context window?
Added 2026-03-03 · 24 runs · 0 drifts
Claude
claude-opus-4-8
YES
100% yes
GPT
gpt-5.5
YES
100% yes
Gemini
gemini-2.5-pro
YES
100% yes
DeepSeek
deepseek-v4-flash
YES
100% yes
Grok
grok-4.3
YES
100% yes