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 Germany. 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 | 1st 77.7% | 6th 59.2% | 4th 74.8% | 2nd 76.6% | 5th 70.8% | 3rd 74.9% | |
| 77.5% | 74% | 79% | 69% | 83% | 80% | 80% | |
| 68.0% | 88% | 0% | 81% | 86% | 73% | 80% | |
| 72.8% | 78% | 77% | 69% | 73% | 67% | 73% | |
| 76.5% | 67% | 91% | 74% | 95% | 61% | 71% | |
| 60.3% | 76% | 0% | 66% | 75% | 78% | 67% | |
| 79.8% | 81% | 82% | 85% | 81% | 65% | 85% | |
| 87.0% | 95% | 96% | 90% | 76% | 85% | 80% | |
| 63.0% | 77% | 0% | 77% | 76% | 72% | 76% | |
| 61.7% | 54% | 76% | 62% | 53% | 59% | 66% | |
| 76.7% | 87% | 91% | 75% | 68% | 68% | 71% |