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 Poland. Source: Global Dialogues GD4 (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 | 3rd 65.9% | 1st 67.5% | 5th 63.6% | 4th 63.7% | 6th 60.5% | 2nd 67.0% | |
| 69.0% | 77% | 74% | 74% | 69% | 52% | 68% | |
| 55.2% | 52% | 59% | 45% | 54% | 63% | 58% | |
| 66.2% | 70% | 62% | 64% | 67% | 62% | 72% | |
| 59.0% | 55% | 58% | 60% | 57% | 62% | 62% | |
| 73.3% | 72% | 78% | 73% | 73% | 72% | 72% | |
| 76.0% | 87% | 73% | 85% | 80% | 58% | 73% | |
| 25.3% | 16% | 33% | 19% | 23% | 23% | 38% | |
| 73.2% | 80% | 77% | 74% | 71% | 66% | 71% | |
| 74.3% | 70% | 83% | 65% | 73% | 76% | 79% | |
| 75.5% | 80% | 78% | 77% | 70% | 71% | 77% |