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 I do not identify with any religious group or faith. 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 84.8% | 2nd 83.0% | 4th 79.0% | 3rd 79.8% | 6th 71.2% | 5th 78.1% | |
| 82.2% | 89% | 75% | 69% | 84% | 86% | 90% | |
| 82.0% | 90% | 88% | 91% | 85% | 51% | 87% | |
| 77.3% | 83% | 82% | 73% | 82% | 67% | 77% | |
| 74.5% | 82% | 69% | 70% | 83% | 64% | 79% | |
| 75.8% | 86% | 81% | 73% | 72% | 68% | 75% | |
| 80.2% | 79% | 85% | 84% | 81% | 71% | 81% | |
| 84.5% | 82% | 92% | 90% | 78% | 87% | 78% | |
| 80.8% | 91% | 83% | 76% | 86% | 66% | 83% | |
| 74.8% | 78% | 86% | 79% | 70% | 75% | 61% | |
| 81.0% | 88% | 89% | 85% | 77% | 77% | 70% |