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 Egypt. 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 | 3rd 60.3% | 1st 63.8% | 6th 57.9% | 4th 59.7% | 5th 58.3% | 2nd 62.4% | |
| 66.3% | 69% | 66% | 69% | 71% | 54% | 69% | |
| 78.5% | 78% | 82% | 64% | 83% | 74% | 90% | |
| 75.8% | 77% | 70% | 81% | 79% | 68% | 80% | |
| 51.7% | 53% | 55% | 47% | 51% | 50% | 54% | |
| 63.7% | 65% | 80% | 55% | 57% | 71% | 54% | |
| 64.2% | 58% | 60% | 78% | 66% | 57% | 66% | |
| 21.2% | 15% | 34% | 12% | 16% | 25% | 25% | |
| 60.0% | 68% | 66% | 60% | 55% | 53% | 58% | |
| 64.7% | 64% | 68% | 63% | 65% | 63% | 65% | |
| 58.0% | 56% | 57% | 50% | 54% | 68% | 63% |