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 Brazil. Source: Global Dialogues GD7 (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 77.3% | 3rd 73.5% | 6th 68.8% | 4th 72.9% | 5th 70.3% | 2nd 74.4% | |
| 61.2% | 66% | 56% | 64% | 51% | 58% | 72% | |
| 62.7% | 71% | 65% | 47% | 65% | 64% | 64% | |
| 78.0% | 76% | 83% | 79% | 76% | 75% | 79% | |
| 72.5% | 83% | 64% | 70% | 73% | 64% | 81% | |
| 78.5% | 79% | 76% | 75% | 79% | 84% | 78% | |
| 81.7% | 94% | 87% | 66% | 84% | 86% | 73% | |
| 73.0% | 75% | 86% | 79% | 72% | 52% | 74% | |
| 65.7% | 67% | 71% | 55% | 69% | 66% | 66% | |
| 80.3% | 86% | 71% | 84% | 77% | 81% | 83% | |
| 75.2% | 76% | 76% | 69% | 83% | 73% | 74% |