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 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 | 1st 73.9% | 4th 69.2% | 2nd 72.9% | 6th 63.8% | 5th 66.3% | 3rd 72.0% | |
| 92.3% | 99% | 66% | 91% | 99% | 99% | 100% | |
| 65.7% | 68% | 70% | 75% | 61% | 58% | 62% | |
| 60.2% | 61% | 64% | 56% | 68% | 53% | 59% | |
| 75.7% | 78% | 78% | 83% | 47% | 91% | 77% | |
| 67.7% | 76% | 37% | 85% | 76% | 58% | 74% | |
| 45.2% | 61% | 61% | 29% | 29% | 39% | 52% | |
| 77.7% | 73% | 90% | 82% | 73% | 73% | 75% | |
| 83.2% | 87% | 89% | 86% | 87% | 76% | 74% | |
| 60.8% | 64% | 65% | 70% | 34% | 57% | 75% | |
| 68.5% | 72% | 72% | 72% | 64% | 59% | 72% |