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 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 | 6th 62.6% | 4th 65.4% | 2nd 68.9% | 5th 64.3% | 1st 70.2% | 3rd 67.5% | |
| 71.2% | 67% | 71% | 80% | 73% | 69% | 67% | |
| 72.7% | 68% | 70% | 71% | 78% | 68% | 81% | |
| 73.0% | 68% | 69% | 77% | 67% | 78% | 79% | |
| 77.0% | 77% | 78% | 78% | 71% | 78% | 80% | |
| 55.2% | 46% | 69% | 51% | 55% | 57% | 53% | |
| 77.2% | 75% | 82% | 76% | 85% | 72% | 73% | |
| 40.5% | 35% | 22% | 48% | 21% | 72% | 45% | |
| 56.8% | 56% | 59% | 61% | 51% | 57% | 57% | |
| 73.5% | 71% | 73% | 73% | 78% | 78% | 68% | |
| 67.8% | 63% | 61% | 74% | 64% | 73% | 72% |