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 Morocco. 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 72.1% | 5th 68.8% | 1st 75.5% | 2nd 74.3% | 6th 67.9% | 4th 70.5% | |
| 73.3% | 78% | 78% | 72% | 72% | 68% | 72% | |
| 81.5% | 82% | 84% | 82% | 84% | 82% | 75% | |
| 61.7% | 62% | 58% | 75% | 56% | 49% | 70% | |
| 75.8% | 70% | 69% | 80% | 84% | 82% | 70% | |
| 59.8% | 69% | 56% | 52% | 59% | 62% | 61% | |
| 62.0% | 61% | 58% | 71% | 66% | 51% | 65% | |
| 67.3% | 61% | 63% | 78% | 66% | 70% | 66% | |
| 73.3% | 78% | 59% | 73% | 82% | 73% | 75% | |
| 80.0% | 77% | 76% | 83% | 90% | 72% | 82% | |
| 80.3% | 83% | 87% | 89% | 84% | 70% | 69% |