Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
Exercises a wide range of blueprint features and point-functions. Includes deterministic checks, JS-based checks, tool-use tracing, multi-turn with assistant:null, prompt weights, citations, and intentional successes/failures.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | GPT 4o Mini | |
|---|---|---|
| Score | 1st 62.6% | |
| 50.0% | 50% | |
| 67.0% | 67% | |
| 75.0% | 75% | |
| 50.0% | 50% | |
| 90.0% | 90% | |
| 0.0% | 0% | |
| 100.0% | 100% |