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 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 | 4th 73.4% | 6th 70.5% | 4th 73.4% | 3rd 74.4% | 1st 77.4% | 2nd 74.5% | |
| 84.3% | 95% | 78% | 78% | 85% | 85% | 85% | |
| 67.3% | 74% | 64% | 70% | 68% | 64% | 64% | |
| 70.8% | 71% | 72% | 72% | 64% | 70% | 76% | |
| 61.8% | 53% | 41% | 81% | 51% | 78% | 67% | |
| 81.0% | 90% | 71% | 77% | 80% | 86% | 82% | |
| 79.5% | 74% | 80% | 81% | 85% | 75% | 82% | |
| 58.5% | 32% | 44% | 63% | 68% | 77% | 67% | |
| 80.0% | 81% | 82% | 74% | 85% | 82% | 76% | |
| 74.5% | 81% | 85% | 71% | 70% | 74% | 66% | |
| 81.5% | 83% | 88% | 67% | 88% | 83% | 80% |