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 United Kingdom. Source: Global Dialogues GD6 (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 80.1% | 3rd 79.5% | 5th 73.9% | 4th 78.6% | 6th 72.7% | 2nd 80.0% | |
| 77.7% | 75% | 84% | 73% | 78% | 76% | 80% | |
| 74.5% | 76% | 79% | 68% | 73% | 74% | 77% | |
| 87.0% | 83% | 89% | 94% | 88% | 85% | 83% | |
| 77.8% | 76% | 68% | 83% | 81% | 77% | 82% | |
| 64.7% | 78% | 61% | 38% | 71% | 70% | 70% | |
| 77.7% | 86% | 83% | 82% | 81% | 58% | 76% | |
| 86.2% | 94% | 92% | 74% | 88% | 79% | 90% | |
| 73.5% | 74% | 74% | 78% | 75% | 60% | 80% | |
| 78.5% | 76% | 80% | 63% | 79% | 84% | 89% | |
| 77.2% | 83% | 85% | 86% | 72% | 64% | 73% |