What Is Eval Gaming?
6.4BRAINROT SCOREEval Gaming Optimizing an AI model specifically to score well on known benchmark tests, rather than to genuinely improve its real-world usefulness — teaching to the test rather than actually getting smarter.
Origin:Named by AI researchers noticing that some model improvements tracked suspiciously closely with public benchmark questions, suggesting labs were optimizing for the test itself rather than general capability.
First Seen:2024
Peak Era:2025-2026 (AI Benchmark Scrutiny Era)
Aura Impact:+10 Aura (Catching Obvious Eval Gaming in a Benchmark Claim) / -5 Aura (Trusting a Benchmark Score at Face Value)
EXAMPLE USAGE
"The benchmark score looks great but real usage feels the same as before, classic eval gaming."
Want the full breakdown — categories, trend velocity, platform distribution, and community voting on Eval Gaming? Visit the full dictionary entry for Eval Gaming.