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 GD7 (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 73.3% | 3rd 71.2% | 5th 69.4% | 2nd 72.4% | 6th 64.9% | 4th 71.0% | |
| 68.7% | 75% | 69% | 68% | 70% | 70% | 60% | |
| 62.0% | 68% | 60% | 59% | 67% | 54% | 64% | |
| 91.2% | 96% | 91% | 96% | 92% | 88% | 84% | |
| 73.7% | 70% | 79% | 74% | 79% | 68% | 72% | |
| 72.7% | 74% | 73% | 68% | 75% | 70% | 76% | |
| 70.3% | 73% | 73% | 69% | 73% | 62% | 72% | |
| 62.7% | 62% | 67% | 59% | 62% | 64% | 62% | |
| 72.0% | 71% | 64% | 84% | 75% | 62% | 76% | |
| 68.2% | 74% | 70% | 64% | 66% | 63% | 72% | |
| 62.3% | 70% | 66% | 53% | 65% | 48% | 72% |