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 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 78.9% | 1st 81.5% | 4th 74.2% | 3rd 77.6% | 6th 70.9% | 5th 73.5% | |
| 87.7% | 92% | 85% | 81% | 91% | 92% | 85% | |
| 80.0% | 83% | 85% | 83% | 80% | 75% | 74% | |
| 72.5% | 75% | 79% | 69% | 74% | 67% | 71% | |
| 76.7% | 82% | 90% | 84% | 78% | 54% | 72% | |
| 77.3% | 80% | 81% | 74% | 74% | 78% | 77% | |
| 75.5% | 77% | 80% | 75% | 75% | 73% | 73% | |
| 75.5% | 67% | 82% | 78% | 72% | 82% | 72% | |
| 69.3% | 72% | 73% | 53% | 76% | 75% | 67% | |
| 74.5% | 88% | 86% | 67% | 80% | 49% | 77% | |
| 72.0% | 73% | 74% | 78% | 76% | 64% | 67% |