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 70.3% | 2nd 70.5% | 4th 68.9% | 1st 73.1% | 6th 64.5% | 5th 67.5% | |
| 59.4% | 61% | 55% | 52% | 64% | 65% | ||
| 72.5% | 74% | 73% | 76% | 71% | 70% | 71% | |
| 67.3% | 69% | 60% | 65% | 74% | 67% | 69% | |
| 61.0% | 60% | 57% | 61% | 73% | 63% | 52% | |
| 56.7% | 72% | 66% | 40% | 61% | 50% | 51% | |
| 76.8% | 82% | 76% | 76% | 82% | 67% | 78% | |
| 69.4% | 61% | 76% | 78% | 66% | 66% | ||
| 71.5% | 72% | 75% | 81% | 75% | 55% | 71% | |
| 75.0% | 79% | 78% | 75% | 76% | 68% | 74% | |
| 80.0% | 73% | 89% | 85% | 75% | 78% |