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 GD7 (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 81.5% | 3rd 86.3% | 6th 80.0% | 1st 86.9% | 4th 82.6% | 2nd 86.4% | |
| 88.5% | 91% | 91% | 85% | 91% | 82% | 91% | |
| 82.8% | 79% | 87% | 69% | 87% | 88% | 87% | |
| 73.3% | 71% | 80% | 59% | 71% | 84% | 75% | |
| 87.3% | 91% | 88% | 81% | 91% | 80% | 93% | |
| 87.5% | 84% | 90% | 84% | 95% | 79% | 93% | |
| 84.5% | 88% | 88% | 72% | 90% | 91% | 78% | |
| 82.5% | 85% | 87% | 89% | 81% | 67% | 86% | |
| 78.2% | 77% | 79% | 77% | 80% | 75% | 81% | |
| 87.8% | 66% | 93% | 98% | 89% | 88% | 93% | |
| 87.0% | 83% | 80% | 86% | 94% | 92% | 87% |