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 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 | 1st 84.2% | 2nd 84.0% | 6th 72.9% | 3rd 83.7% | 3rd 83.7% | 5th 82.1% | |
| 73.8% | 66% | 77% | 62% | 69% | 84% | 85% | |
| 78.0% | 93% | 84% | 63% | 75% | 86% | 67% | |
| 87.0% | 85% | 91% | 84% | 91% | 89% | 82% | |
| 83.8% | 86% | 85% | 81% | 86% | 82% | 83% | |
| 76.3% | 85% | 72% | 48% | 83% | 87% | 83% | |
| 84.5% | 84% | 82% | 77% | 82% | 88% | 94% | |
| 82.2% | 86% | 84% | 72% | 84% | 84% | 83% | |
| 84.2% | 85% | 87% | 77% | 92% | 81% | 83% | |
| 81.0% | 81% | 83% | 72% | 88% | 78% | 84% | |
| 86.8% | 91% | 95% | 93% | 87% | 78% | 77% |