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 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 77.0% | 1st 80.3% | 6th 64.2% | 5th 74.0% | 2nd 78.5% | 4th 75.5% | |
| 83.0% | 87% | 82% | 83% | 88% | 69% | 89% | |
| 67.7% | 71% | 67% | 58% | 67% | 73% | 70% | |
| 86.2% | 89% | 84% | 86% | 88% | 90% | 80% | |
| 86.5% | 86% | 90% | 81% | 79% | 91% | 92% | |
| 75.0% | 73% | 97% | 66% | 72% | 77% | 65% | |
| 74.0% | 79% | 81% | 60% | 68% | 79% | 77% | |
| 57.0% | 52% | 69% | 46% | 59% | 57% | 59% | |
| 74.5% | 88% | 76% | 52% | 70% | 91% | 70% | |
| 75.0% | 76% | 83% | 54% | 76% | 81% | 80% | |
| 70.3% | 69% | 74% | 56% | 73% | 77% | 73% |