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 Pakistan. 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 76.2% | 5th 71.9% | 3rd 77.0% | 1st 77.2% | 6th 68.1% | 1st 77.2% | |
| 70.5% | 69% | 68% | 78% | 73% | 62% | 73% | |
| 62.0% | 59% | 44% | 68% | 64% | 61% | 76% | |
| 86.2% | 93% | 82% | 74% | 90% | 88% | 90% | |
| 72.3% | 68% | 73% | 67% | 76% | 83% | 67% | |
| 77.7% | 78% | 87% | 83% | 85% | 59% | 74% | |
| 83.2% | 86% | 88% | 86% | 85% | 67% | 87% | |
| 76.0% | 71% | 74% | 77% | 69% | 82% | 83% | |
| 79.7% | 88% | 83% | 81% | 87% | 63% | 76% | |
| 72.2% | 77% | 55% | 84% | 70% | 63% | 84% | |
| 66.3% | 73% | 65% | 72% | 73% | 53% | 62% |