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 Spain. Source: Global Dialogues GD6 (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 | 6th 65.0% | 1st 70.9% | 5th 67.9% | 2nd 70.2% | 4th 68.9% | 3rd 69.5% | |
| 43.3% | 38% | 46% | 40% | 40% | 44% | 52% | |
| 75.5% | 75% | 81% | 78% | 69% | 76% | 74% | |
| 83.2% | 83% | 76% | 74% | 94% | 90% | 82% | |
| 74.2% | 68% | 72% | 69% | 85% | 87% | 64% | |
| 75.8% | 71% | 78% | 64% | 75% | 82% | 85% | |
| 60.5% | 61% | 68% | 64% | 61% | 49% | 60% | |
| 48.2% | 42% | 52% | 56% | 44% | 44% | 51% | |
| 75.2% | 75% | 81% | 68% | 81% | 76% | 70% | |
| 65.7% | 58% | 68% | 75% | 70% | 53% | 70% | |
| 85.8% | 79% | 87% | 91% | 83% | 88% | 87% |