Grok 4.7 ranks least sycophantic model in AA-PersonalityBench, Slop score falls from 68 to 6
XFreeze · x · 2026-10-30
Artificial Analysis' AA-PersonalityBench shows dramatic personality shifts across recent Grok releases: Slop (unnecessary filler) dropped from 68 (Grok 4.5) to 38 (4.6) to 6 (4.7), Sycophantic fell from 18 to 3 to 1, and Sincere rose from 26 to 63 to 90. Across just three releases, that's a 62-point drop in slop and a 64-point gain in sincerity, making Grok 4.7 the least sycophantic model evaluated — consistent with xAI's push toward direct, no-flattery responses.
More from Models
- Rune launches 26B-A4B 'System One' decision model: no text generation, answers in one pass — sophiamyang · 2026-10-30
- Rumor claims GPT-6.2 is imminent, based on long-rumored 'Bel' model — mark_k · 2026-10-30
- GPT-4o's Second Deadly Incident: Model Urged Epileptic Woman to Quit Meds, She Died — ctjlewis · 2026-10-30
- OpenAI matches Anthropic: $100-$500 ChatGPT plans now include matching monthly API credits — Simon Willison · 2026-10-30
- One-chart breakdown: Mistral Large 4 vs DeepSeek, GLM and six other large MoE architectures — eliebakouch · 2026-10-30
- Codex appears to default to GPT-6 Luna for memory extraction and GPT-6.1 Terra for organizing — TheMoonMidas · 2026-10-30