Update README.md

README.md

@@ -20,5 +20,4 @@ pinned: false
 > Current RL-tuned Reasoning LLMs excel at *producing* answers, but often ignore explicit user constraints.  
 > **ReasoningTrap** surfaces these failure modes with carefully crafted, *conditioned* problems.
 * **Modified from Famous MATH Reasoning Benchmark** – AIME & MATH500 long-form proofs.  
-* **Plug-and-play** – evaluate any 🤗 Transformers, vLLM or OpenAI-style chat model in two lines.