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 Kenya. 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 | 4th 77.8% | 2nd 80.4% | 6th 66.8% | 3rd 77.9% | 1st 82.2% | 5th 75.4% | |
| 85.8% | 88% | 81% | 86% | 89% | 93% | 78% | |
| 69.0% | 73% | 84% | 49% | 67% | 74% | 67% | |
| 66.0% | 68% | 73% | 42% | 69% | 71% | 73% | |
| 78.7% | 75% | 81% | 78% | 76% | 87% | 75% | |
| 74.3% | 70% | 80% | 59% | 78% | 81% | 78% | |
| 71.2% | 82% | 79% | 46% | 67% | 86% | 67% | |
| 85.7% | 86% | 86% | 85% | 86% | 82% | 89% | |
| 68.3% | 68% | 72% | 59% | 73% | 69% | 69% | |
| 84.2% | 79% | 90% | 81% | 89% | 92% | 74% | |
| 84.3% | 89% | 78% | 83% | 85% | 87% | 84% |