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 GD6 (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 | 2nd 84.5% | 3rd 83.2% | 5th 77.3% | 1st 84.7% | 6th 76.1% | 4th 82.7% | |
| 80.0% | 77% | 87% | 83% | 80% | 73% | 80% | |
| 81.8% | 89% | 81% | 79% | 75% | 94% | 73% | |
| 87.7% | 89% | 87% | 89% | 93% | 83% | 85% | |
| 71.2% | 68% | 69% | 69% | 78% | 65% | 78% | |
| 80.0% | 87% | 77% | 60% | 90% | 86% | 80% | |
| 87.5% | 94% | 91% | 84% | 89% | 74% | 93% | |
| 81.0% | 86% | 81% | 75% | 81% | 83% | 80% | |
| 80.8% | 85% | 83% | 76% | 86% | 69% | 86% | |
| 85.2% | 95% | 93% | 71% | 90% | 76% | 86% | |
| 79.0% | 75% | 83% | 87% | 85% | 58% | 86% |