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 | 1st 81.0% | 2nd 80.0% | 4th 76.3% | 3rd 78.5% | 6th 71.6% | 5th 75.4% | |
| 89.5% | 90% | 91% | 81% | 88% | 94% | 93% | |
| 77.0% | 81% | 80% | 89% | 81% | 57% | 74% | |
| 72.2% | 76% | 75% | 73% | 76% | 58% | 75% | |
| 73.2% | 75% | 85% | 67% | 86% | 56% | 70% | |
| 78.2% | 81% | 74% | 77% | 80% | 78% | 79% | |
| 79.0% | 85% | 87% | 76% | 77% | 74% | 75% | |
| 79.2% | 74% | 84% | 82% | 75% | 79% | 81% | |
| 73.3% | 83% | 75% | 70% | 70% | 72% | 70% | |
| 81.3% | 89% | 81% | 82% | 81% | 79% | 76% | |
| 68.5% | 76% | 68% | 66% | 71% | 69% | 61% |