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 Other religious group. 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 65.8% | 2nd 65.8% | 6th 64.7% | 5th 65.2% | 1st 66.5% | 4th 65.3% | |
| 44.5% | 36% | 54% | 25% | 50% | 51% | 51% | |
| 70.5% | 71% | 71% | 74% | 68% | 76% | 63% | |
| 61.2% | 54% | 54% | 65% | 60% | 76% | 58% | |
| 57.8% | 50% | 47% | 59% | 62% | 68% | 61% | |
| 59.2% | 60% | 75% | 59% | 51% | 48% | 62% | |
| 70.7% | 72% | 63% | 76% | 73% | 73% | 67% | |
| 75.7% | 90% | 69% | 76% | 73% | 71% | 75% | |
| 72.3% | 78% | 74% | 77% | 67% | 69% | 69% | |
| 81.3% | 81% | 85% | 84% | 86% | 68% | 84% | |
| 62.3% | 66% | 66% | 52% | 62% | 65% | 63% |