agentic tasks
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Jul 14, 2025 by Pratik Bhavsar · across every show →
Everything said about agentic tasks, oldest first
Jul 14, 2025 neutral
General LLM benchmark rankings do not translate to agent performance
“What we have understood from our previous experiments is that it's not necessary that what you see as top models, In let's say LM arena or other specific evaluation or general evaluations, they might not be also the same ranking for other tasks like agentic ta…”