Home/AI Incident Database/"Reflection 70B" claims of beating GPT-4o collapse as researchers find the demo routes to Claude
"Reflection 70B" claims of beating GPT-4o collapse as researchers find the demo routes to Claude
A model announced as the world's best open LLM turned out to underperform, and its hosted demo was found to be calling Anthropic's Claude, damaging trust in self-reported benchmarks.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.
