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 GD7 (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 | 2nd 74.9% | 5th 70.6% | 3rd 73.9% | 1st 75.6% | 6th 70.5% | 4th 72.2% | |
| 72.2% | 76% | 70% | 75% | 73% | 70% | 69% | |
| 62.2% | 64% | 58% | 66% | 61% | 60% | 64% | |
| 84.0% | 71% | 97% | 81% | 84% | 90% | 81% | |
| 79.5% | 82% | 76% | 87% | 77% | 75% | 80% | |
| 61.2% | 62% | 64% | 59% | 60% | 62% | 60% | |
| 84.8% | 91% | 76% | 84% | 89% | 81% | 88% | |
| 65.3% | 66% | 65% | 66% | 75% | 60% | 60% | |
| 54.3% | 63% | 38% | 61% | 67% | 48% | 49% | |
| 85.8% | 85% | 87% | 82% | 84% | 92% | 85% | |
| 80.2% | 89% | 75% | 78% | 86% | 67% | 86% |