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 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 | 3rd 71.9% | 4th 71.8% | 2nd 72.7% | 5th 71.3% | 6th 68.1% | 1st 74.7% | |
| 62.5% | 57% | 54% | 53% | 63% | 75% | 73% | |
| 83.5% | 79% | 81% | 80% | 85% | 87% | 89% | |
| 73.7% | 70% | 78% | 74% | 70% | 79% | 71% | |
| 74.3% | 66% | 60% | 86% | 73% | 76% | 85% | |
| 52.0% | 67% | 56% | 29% | 54% | 54% | 52% | |
| 74.2% | 81% | 75% | 79% | 78% | 57% | 75% | |
| 70.3% | 64% | 72% | 77% | 69% | 64% | 76% | |
| 72.8% | 74% | 74% | 83% | 69% | 60% | 77% | |
| 73.0% | 76% | 75% | 78% | 74% | 61% | 74% | |
| 81.2% | 85% | 93% | 88% | 78% | 68% | 75% |