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 | 3rd 79.2% | 4th 78.6% | 5th 77.5% | 1st 83.4% | 2nd 81.2% | 6th 77.3% | |
| 72.8% | 71% | 67% | 74% | 81% | 73% | 71% | |
| 79.8% | 83% | 87% | 67% | 77% | 84% | 81% | |
| 82.2% | 86% | 81% | 81% | 85% | 80% | 80% | |
| 88.8% | 84% | 94% | 86% | 97% | 84% | 88% | |
| 80.8% | 81% | 79% | 73% | 87% | 83% | 82% | |
| 64.3% | 62% | 68% | 64% | 63% | 72% | 57% | |
| 82.8% | 79% | 80% | 78% | 92% | 91% | 77% | |
| 83.0% | 88% | 86% | 85% | 80% | 85% | 74% | |
| 76.7% | 77% | 65% | 78% | 79% | 79% | 82% | |
| 84.0% | 81% | 79% | 89% | 93% | 81% | 81% |