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 GD5 (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 | 1st 81.1% | 5th 75.0% | 6th 73.8% | 2nd 79.8% | 4th 78.4% | 3rd 79.4% | |
| 69.8% | 73% | 67% | 65% | 76% | 69% | 69% | |
| 79.2% | 82% | 85% | 68% | 80% | 79% | 81% | |
| 79.0% | 82% | 81% | 67% | 79% | 81% | 84% | |
| 86.7% | 96% | 92% | 70% | 94% | 86% | 82% | |
| 84.5% | 81% | 80% | 90% | 87% | 87% | 82% | |
| 58.8% | 69% | 58% | 58% | 51% | 54% | 63% | |
| 77.3% | 75% | 73% | 78% | 77% | 87% | 74% | |
| 88.2% | 95% | 86% | 85% | 79% | 91% | 93% | |
| 70.8% | 79% | 53% | 70% | 81% | 60% | 82% | |
| 84.8% | 79% | 75% | 87% | 94% | 90% | 84% |