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 GD5 (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 66.9% | 1st 71.7% | 6th 63.0% | 2nd 67.5% | 4th 66.6% | 5th 65.1% | |
| 47.5% | 43% | 51% | 36% | 55% | 51% | 49% | |
| 52.8% | 56% | 61% | 49% | 51% | 50% | 50% | |
| 59.0% | 61% | 67% | 52% | 65% | 58% | 51% | |
| 79.3% | 78% | 89% | 79% | 79% | 78% | 73% | |
| 55.0% | 57% | 52% | 49% | 52% | 61% | 59% | |
| 69.3% | 79% | 73% | 55% | 84% | 63% | 62% | |
| 76.8% | 74% | 86% | 81% | 70% | 75% | 75% | |
| 79.2% | 76% | 81% | 80% | 80% | 73% | 85% | |
| 62.0% | 59% | 76% | 64% | 49% | 67% | 57% | |
| 87.0% | 86% | 81% | 85% | 90% | 90% | 90% |