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 Portugal. 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 | 3rd 71.5% | 1st 73.5% | 4th 71.3% | 6th 69.8% | 5th 70.2% | 2nd 71.9% | |
| 67.0% | 63% | 69% | 75% | 62% | 68% | 65% | |
| 73.5% | 75% | 80% | 67% | 80% | 71% | 68% | |
| 77.0% | 75% | 84% | 74% | 75% | 80% | 74% | |
| 77.5% | 81% | 82% | 83% | 75% | 69% | 75% | |
| 76.5% | 75% | 73% | 90% | 69% | 73% | 79% | |
| 79.2% | 79% | 74% | 80% | 70% | 83% | 89% | |
| 68.8% | 70% | 73% | 63% | 70% | 73% | 64% | |
| 58.2% | 60% | 61% | 59% | 53% | 49% | 67% | |
| 73.7% | 76% | 76% | 65% | 75% | 74% | 76% | |
| 62.3% | 61% | 63% | 57% | 69% | 62% | 62% |