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 | 6th 64.4% | 1st 68.2% | 2nd 66.5% | 5th 65.0% | 4th 65.4% | 3rd 66.3% | |
| 73.2% | 72% | 79% | 76% | 70% | 67% | 75% | |
| 60.3% | 70% | 65% | 46% | 68% | 63% | 50% | |
| 73.2% | 67% | 78% | 69% | 71% | 81% | 73% | |
| 76.5% | 74% | 77% | 81% | 75% | 75% | 77% | |
| 48.5% | 46% | 47% | 53% | 44% | 48% | 53% | |
| 61.7% | 56% | 65% | 76% | 51% | 59% | 63% | |
| 53.3% | 46% | 54% | 61% | 54% | 51% | 54% | |
| 76.3% | 74% | 77% | 76% | 81% | 68% | 82% | |
| 70.7% | 69% | 78% | 68% | 67% | 75% | 67% | |
| 66.0% | 70% | 62% | 59% | 69% | 67% | 69% |