Strengths and considerations
- The linked evaluation identifies the paper-specific dataset and assessment rather than treating the task name as a universal benchmark.PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, ESM-2 8M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column; Table 1, ESM-C 300M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column