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 75.8% | 2nd 74.4% | 5th 68.3% | 3rd 71.4% | 6th 64.1% | 4th 70.7% | |
| 72.8% | 80% | 79% | 69% | 71% | 65% | 73% | |
| 90.0% | 93% | 95% | 81% | 88% | 92% | 91% | |
| 83.0% | 91% | 81% | 83% | 87% | 69% | 87% | |
| 74.8% | 85% | 78% | 66% | 68% | 76% | 76% | |
| 74.0% | 72% | 81% | 65% | 74% | 79% | 73% | |
| 65.0% | 74% | 68% | 72% | 71% | 44% | 61% | |
| 34.5% | 35% | 41% | 26% | 36% | 35% | 34% | |
| 74.8% | 81% | 80% | 83% | 71% | 59% | 75% | |
| 67.0% | 65% | 71% | 64% | 71% | 65% | 66% | |
| 71.8% | 82% | 70% | 74% | 77% | 57% | 71% |