Claude-2.1

• Claude 2.1 on ARC: Score Breakdown
• Claude 2.1 on BBH (BIG-Bench Hard): Score Breakdown
• Claude 2.1 on GPQA: Score Breakdown
• Claude 2.1 on GSM8K (Grade School Math 8K): Score Breakdown
• Claude 2.1 on HumanEval: Score Breakdown
• Claude 2.1 on IFEval: Score Breakdown
• Claude 2.1 on MATH: Score Breakdown
• Claude 2.1 on MMLU (Massive Multitask Language Understanding): Score Breakdown
• Claude 2.1 on MUSR: Score Breakdown
• Claude 2.1 on WinoGrande: Score Breakdown