The proliferation of AI leaderboards incentivizes companies to optimize models for specific benchmarks. This creates a risk of "acing the SATs" where models excel on tests but don't necessarily make progress on solving real-world problems. This focus on gaming metrics could diverge from creating genuine user value.

Public leaderboards like LM Arena are becoming unreliable proxies for model performance. Teams implicitly or explicitly "benchmark" by optimizing for specific test sets. The superior strategy is to focus on internal, proprietary evaluation metrics and use public benchmarks only as a final, confirmatory check, not as a primary development target.

To ensure AI labs don't provide specially optimized private endpoints for evaluation, the firm creates anonymous accounts to test the same public models everyone else uses. This "mystery shopper" policy maintains the integrity and independence of their results.

To ensure they are testing the same models available to the public, they register anonymous accounts to run evals. This prevents labs from providing specially tuned private endpoints that perform better than their publicly available APIs, thereby maintaining the integrity of their independent analysis.

An analysis suggests most AI startups claiming proprietary tech are just wrappers around major LLMs. This can be verified by 'fingerprinting' their APIs; if a startup's service has the exact same unique, exponential rate-limiting pattern as OpenAI's, it's a clear sign they are just reselling the underlying service.

The gap between benchmark scores and real-world performance suggests labs achieve high scores by distilling superior models or training for specific evals. This makes benchmarks a poor proxy for genuine capability, a skepticism that should be applied to all new model releases.

As developers increasingly use AI coding assistants like Claude Code, they flood public repositories like GitHub with high-quality, AI-generated outputs. This effectively turns the internet into a massive, unavoidable training dataset for competing models, making it difficult to police "distillation" as a violation of terms.

To ensure they're testing publicly available models, Artificial Analysis creates anonymous accounts to run benchmarks without the provider's knowledge. Labs agree to this policy because it guarantees fairness and prevents their competitors from receiving special treatment or manipulating results, creating a stable, trusted equilibrium.

Anthropic's choice to label data collection by Chinese labs as a 'distillation attack' is a strategic branding move. This framing aligns with their public image focused on AI safety and geopolitical concerns, rather than just being a technical description of the activity.