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.
DTEF: Predict response distributions for Christianity. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | |
|---|---|---|---|---|---|---|---|
| Score | 5th 75.2% | 1st 83.8% | 6th 72.9% | 4th 79.0% | 2nd 81.1% | 3rd 79.1% | |
| 85.5% | 88% | 89% | 90% | 80% | 79% | 87% | |
| 73.8% | 73% | 69% | 70% | 76% | 77% | 78% | |
| 88.8% | 82% | 95% | 91% | 89% | 88% | 88% | |
| 78.5% | 73% | 87% | 68% | 78% | 88% | 77% | |
| 81.2% | 74% | 91% | 77% | 80% | 85% | 80% | |
| 86.0% | 88% | 87% | 76% | 90% | 85% | 90% | |
| 51.3% | 34% | 67% | 51% | 52% | 51% | 53% | |
| 80.8% | 82% | 81% | 72% | 84% | 88% | 78% | |
| 72.8% | 77% | 76% | 55% | 68% | 88% | 73% | |
| 86.3% | 81% | 96% | 79% | 93% | 82% | 87% |