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 | 2nd 79.2% | 4th 76.2% | 6th 72.3% | 1st 80.4% | 5th 74.0% | 3rd 78.2% | |
| 76.8% | 82% | 74% | 68% | 81% | 75% | 81% | |
| 74.8% | 80% | 75% | 63% | 75% | 76% | 80% | |
| 82.0% | 84% | 84% | 78% | 82% | 82% | 82% | |
| 79.2% | 90% | 92% | 72% | 92% | 62% | 67% | |
| 77.5% | 79% | 81% | 78% | 75% | 79% | 73% | |
| 69.5% | 71% | 73% | 71% | 76% | 58% | 68% | |
| 83.7% | 87% | 77% | 76% | 85% | 91% | 86% | |
| 70.2% | 74% | 65% | 57% | 75% | 76% | 74% | |
| 73.2% | 68% | 67% | 84% | 75% | 57% | 88% | |
| 80.3% | 77% | 74% | 76% | 88% | 84% | 83% |