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 Germany. Source: Global Dialogues GD2 (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 | 4th 69.7% | 1st 75.3% | 6th 67.0% | 5th 68.7% | 2nd 73.7% | 3rd 73.3% | |
| 65.0% | 58% | 75% | 59% | 64% | 66% | 68% | |
| 70.2% | 74% | 72% | 75% | 59% | 72% | 69% | |
| 78.7% | 77% | 79% | 67% | 83% | 83% | 83% |