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 | 1st 68.2% | 5th 62.1% | 3rd 64.8% | 4th 64.7% | 6th 61.9% | 2nd 65.1% | |
| 74.8% | 77% | 77% | 76% | 79% | 71% | 69% | |
| 56.2% | 63% | 51% | 63% | 58% | 44% | 58% | |
| 68.3% | 71% | 64% | 72% | 70% | 58% | 75% | |
| 47.5% | 52% | 36% | 50% | 55% | 39% | 53% | |
| 70.0% | 67% | 80% | 64% | 72% | 73% | 64% | |
| 77.5% | 79% | 83% | 73% | 80% | 70% | 80% | |
| 25.3% | 42% | 8% | 41% | 5% | 23% | 33% | |
| 76.0% | 80% | 76% | 66% | 80% | 80% | 74% | |
| 74.2% | 73% | 78% | 69% | 72% | 81% | 72% | |
| 74.8% | 78% | 68% | 74% | 76% | 80% | 73% |