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 Morocco. Source: Global Dialogues GD5 (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 | 2nd 72.8% | 3rd 70.7% | 6th 68.0% | 1st 73.8% | 5th 69.5% | 4th 70.4% | |
| 65.3% | 73% | 62% | 61% | 77% | 55% | 64% | |
| 79.2% | 82% | 82% | 86% | 83% | 69% | 73% | |
| 78.5% | 81% | 79% | 67% | 80% | 86% | 78% | |
| 76.7% | 82% | 98% | 63% | 79% | 71% | 67% | |
| 55.5% | 54% | 46% | 57% | 57% | 53% | 66% | |
| 67.8% | 64% | 72% | 69% | 65% | 68% | 69% | |
| 74.5% | 74% | 69% | 82% | 83% | 70% | 69% | |
| 64.3% | 53% | 62% | 75% | 66% | 67% | 63% | |
| 67.8% | 79% | 59% | 46% | 69% | 78% | 76% | |
| 79.0% | 86% | 78% | 74% | 79% | 78% | 79% |