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 GD5 (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 | 2nd 67.2% | 5th 59.1% | 4th 62.0% | 1st 67.6% | 6th 58.1% | 3rd 63.6% | |
| 72.2% | 68% | 74% | 67% | 79% | 73% | ||
| 59.2% | 65% | 56% | 70% | 59% | 46% | 59% | |
| 77.2% | 82% | 81% | 79% | 68% | 76% | ||
| 84.4% | 89% | 91% | 96% | 64% | 82% | ||
| 45.0% | 51% | 29% | 54% | 42% | 49% | ||
| 71.8% | 67% | 67% | 78% | 78% | 69% | ||
| 68.0% | 65% | 64% | 75% | 67% | 69% | ||
| 45.2% | 64% | 10% | 56% | 38% | 58% | ||
| 51.8% | 56% | 56% | 50% | 50% | 47% | ||
| 57.8% | 65% | 63% | 54% | 62% | 49% | 54% |