Study Finds Discrepancies in AI Benchmark Accuracy Across Models
AI labs inflate benchmark scores by an average of 6.4%—discover why independent tests differ and how this impacts real‑world model performance.
2 minutes to read
CHEMOURS CO/THE
China’s open-weight AI models trail US closed models by seven months
New benchmark data shows China’s open-weight AI models are only seven months behind U.S. closed models, revealing a shrinking performance gap and new market dynamics.
2 minutes to read