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 Italy. 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 | 1st 75.1% | 2nd 72.3% | 5th 69.3% | 4th 69.4% | 6th 63.3% | 3rd 70.9% | |
| 72.1% | 80% | 75% | 69% | 72% | 65% | 73% | |
| 89.8% | 93% | 98% | 81% | 84% | 92% | 91% | |
| 81.5% | 92% | 72% | 85% | 82% | 71% | 88% | |
| 74.3% | 80% | 78% | 68% | 68% | 76% | 76% | |
| 71.7% | 72% | 78% | 66% | 72% | 70% | 74% | |
| 64.3% | 74% | 65% | 72% | 70% | 44% | 61% | |
| 34.9% | 35% | 41% | 30% | 36% | 34% | 34% | |
| 73.1% | 81% | 69% | 83% | 69% | 60% | 77% | |
| 65.8% | 63% | 73% | 64% | 68% | 64% | 63% | |
| 73.3% | 83% | 76% | 76% | 75% | 59% | 72% |