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 GD4 (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 | 4th 61.9% | 3rd 62.2% | 6th 58.9% | 2nd 62.6% | 1st 64.3% | 5th 59.3% | |
| 61.3% | 59% | 67% | 67% | 59% | 57% | 59% | |
| 71.5% | 65% | 68% | 68% | 78% | 79% | 71% | |
| 80.5% | 82% | 79% | 75% | 88% | 82% | 77% | |
| 68.5% | 68% | 71% | 70% | 72% | 65% | 65% | |
| 68.0% | 64% | 79% | 53% | 70% | 80% | 62% | |
| 63.7% | 65% | 69% | 69% | 63% | 54% | 62% | |
| 20.7% | 32% | 6% | 19% | 11% | 32% | 24% | |
| 57.2% | 64% | 55% | 48% | 58% | 67% | 51% | |
| 59.8% | 55% | 62% | 58% | 60% | 65% | 59% | |
| 64.2% | 65% | 66% | 62% | 67% | 62% | 63% |