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 France. 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 | 5th 64.0% | 1st 67.0% | 3rd 66.9% | 2nd 67.0% | 6th 63.5% | 4th 64.3% | |
| 71.7% | 76% | 79% | 75% | 68% | 66% | 66% | |
| 59.2% | 63% | 65% | 41% | 67% | 69% | 50% | |
| 74.8% | 80% | 78% | 69% | 72% | 77% | 73% | |
| 78.3% | 75% | 77% | 84% | 81% | 76% | 77% | |
| 49.2% | 43% | 47% | 55% | 56% | 50% | 44% | |
| 60.3% | 55% | 65% | 75% | 56% | 48% | 63% | |
| 53.7% | 48% | 49% | 66% | 52% | 51% | 56% | |
| 73.8% | 77% | 73% | 74% | 73% | 69% | 77% | |
| 69.3% | 71% | 75% | 71% | 72% | 60% | 67% | |
| 64.2% | 52% | 62% | 59% | 73% | 69% | 70% |