Claude Research may show only a small usage gap between models
shows a surprisingly small usage difference when the same prompt is used with different settings. Sonnet on low effort often ends at about 49% of the 5-hour . Opus on max effort ends at about 53%.
The visible gap is only 4 percentage points. The open question is whether the feature itself uses so much that it hides the model difference, or whether the usage display does not clearly reflect the real cost difference.
Key points
- was tested with the same prompt under two different settings.
- Sonnet on low effort appeared to use about 49% of the 5-hour .
- Opus on max effort appeared to use about 53%.
- The small visible gap raises questions about or the usage display.