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 65+. 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 | 3rd 63.8% | 1st 68.7% | 6th 61.5% | 4th 63.5% | 2nd 65.4% | 5th 62.2% | |
| 66.3% | 62% | 75% | 55% | 68% | 72% | 66% | |
| 74.3% | 75% | 77% | 70% | 74% | 76% | 74% | |
| 60.2% | 60% | 67% | 51% | 58% | 67% | 58% | |
| 77.5% | 77% | 79% | 92% | 77% | 84% | 56% | |
| 78.3% | 78% | 87% | 77% | 78% | 72% | 78% | |
| 48.5% | 49% | 53% | 54% | 36% | 46% | 53% | |
| 71.7% | 66% | 64% | 71% | 79% | 79% | 71% | |
| 52.3% | 58% | 50% | 50% | 55% | 46% | 55% | |
| 64.0% | 61% | 77% | 54% | 58% | 68% | 66% | |
| 48.7% | 52% | 58% | 41% | 52% | 44% | 45% |