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 Mexico. 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 | 1st 69.1% | 3rd 67.2% | 5th 65.6% | 4th 65.9% | 6th 61.1% | 2nd 67.3% | |
| 58.0% | 56% | 59% | 57% | 56% | 57% | 63% | |
| 68.0% | 79% | 78% | 72% | 47% | 77% | 55% | |
| 61.5% | 66% | 61% | 59% | 60% | 50% | 73% | |
| 55.2% | 60% | 49% | 49% | 60% | 60% | 53% | |
| 57.3% | 61% | 63% | 51% | 54% | 65% | 50% | |
| 72.8% | 69% | 78% | 78% | 79% | 49% | 84% | |
| 74.3% | 77% | 81% | 66% | 75% | 68% | 79% | |
| 75.5% | 82% | 70% | 80% | 79% | 74% | 68% | |
| 66.5% | 60% | 60% | 75% | 68% | 62% | 74% | |
| 71.2% | 81% | 73% | 69% | 81% | 49% | 74% |