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 Vietnam. 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 | 1st 80.9% | 3rd 77.7% | 6th 71.2% | 2nd 79.2% | 4th 77.2% | 5th 76.3% | |
| 74.5% | 78% | 63% | 80% | 77% | 63% | 86% | |
| 83.8% | 90% | 88% | 57% | 90% | 89% | 89% | |
| 69.8% | 66% | 65% | 89% | 69% | 65% | 65% | |
| 73.7% | 73% | 69% | 72% | 78% | 73% | 77% | |
| 76.8% | 83% | 88% | 51% | 79% | 87% | 73% | |
| 79.0% | 90% | 89% | 65% | 78% | 79% | 73% | |
| 76.0% | 91% | 86% | 59% | 78% | 79% | 63% | |
| 74.0% | 70% | 79% | 65% | 80% | 73% | 77% | |
| 85.2% | 79% | 81% | 90% | 88% | 92% | 81% | |
| 78.0% | 89% | 69% | 84% | 75% | 72% | 79% |