Last updated: Oct 14, 2025

Welcome to the LLM Stats community. We’re a space for thoughtful, evidence-based conversations about language models, benchmarks, methodology, and real-world impact.

Purpose of the community

• Share reliable information and analysis about LLMs and AI systems
• Encourage transparent, data-driven discussion and respectful debate
• Support practitioners, researchers, and interested readers in understanding the state of the field

Do’s and don’ts

• Do: be respectful; critique ideas with evidence; stay on topic; cite sources; disclose affiliations/conflicts.
• Don’t: engage in personal attacks, harassment, dogpiling, brigading, trolling, or sealioning; spread misinformation; derail threads.

Prohibited actions

• Harassment, hate speech, discrimination, threats, sexualization, and doxxing
• Defamation, knowingly false claims, and impersonation
• Spam, scams, fraud, malware, or deceptive links
• Coordinated manipulation (e.g., astroturfing, vote/visibility gaming)
• Circumvention of moderation or technical safeguards