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 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 | 6th 64.6% | 2nd 68.2% | 1st 69.0% | 3rd 66.3% | 5th 65.8% | 4th 66.2% | |
| 44.5% | 47% | 46% | 47% | 35% | 35% | 57% | |
| 53.0% | 56% | 58% | 43% | 61% | 57% | 43% | |
| 81.2% | 79% | 79% | 81% | 86% | 86% | 76% | |
| 71.7% | 68% | 83% | 78% | 69% | 58% | 74% | |
| 76.0% | 77% | 71% | 75% | 77% | 76% | 80% | |
| 62.3% | 59% | 57% | 76% | 56% | 63% | 63% | |
| 59.3% | 55% | 59% | 69% | 60% | 57% | 56% | |
| 64.3% | 65% | 66% | 77% | 59% | 63% | 56% | |
| 87.2% | 80% | 92% | 84% | 87% | 92% | 88% | |
| 67.3% | 60% | 71% | 60% | 73% | 71% | 69% |