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 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 | 4th 78.1% | 1st 80.0% | 6th 74.0% | 2nd 79.6% | 5th 77.3% | 3rd 78.8% | |
| 75.7% | 75% | 72% | 72% | 76% | 79% | 80% | |
| 73.5% | 74% | 72% | 68% | 70% | 75% | 82% | |
| 79.2% | 80% | 84% | 68% | 85% | 79% | 79% | |
| 72.7% | 77% | 81% | 77% | 79% | 47% | 75% | |
| 79.3% | 88% | 87% | 69% | 75% | 83% | 74% | |
| 77.7% | 76% | 85% | 76% | 77% | 79% | 73% | |
| 84.7% | 83% | 79% | 80% | 87% | 88% | 91% | |
| 72.8% | 75% | 64% | 58% | 76% | 88% | 76% | |
| 82.7% | 77% | 89% | 87% | 86% | 75% | 82% | |
| 81.5% | 76% | 87% | 85% | 85% | 80% | 76% |