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 United States. Source: Global Dialogues GD4 (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 | 4th 79.0% | 5th 75.0% | 6th 72.5% | 2nd 80.2% | 1st 81.2% | 3rd 79.8% | |
| 81.0% | 82% | 80% | 76% | 84% | 84% | 80% | |
| 79.3% | 83% | 70% | 74% | 84% | 84% | 81% | |
| 86.8% | 84% | 87% | 86% | 88% | 89% | 87% | |
| 83.5% | 82% | 87% | 78% | 88% | 81% | 85% | |
| 80.0% | 80% | 91% | 63% | 84% | 83% | 79% | |
| 82.0% | 85% | 71% | 75% | 86% | 89% | 86% | |
| 54.5% | 60% | 29% | 69% | 45% | 60% | 64% | |
| 75.5% | 82% | 72% | 66% | 79% | 78% | 76% | |
| 70.7% | 63% | 78% | 65% | 74% | 73% | 71% | |
| 86.2% | 89% | 85% | 73% | 90% | 91% | 89% |