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 GD6 (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 76.1% | 1st 76.7% | 6th 69.7% | 5th 74.6% | 2nd 76.3% | 4th 75.0% | |
| 75.5% | 81% | 80% | 77% | 67% | 80% | 68% | |
| 79.5% | 87% | 89% | 61% | 73% | 82% | 85% | |
| 87.2% | 83% | 91% | 90% | 82% | 92% | 85% | |
| 69.3% | 66% | 63% | 65% | 71% | 72% | 79% | |
| 60.3% | 79% | 48% | 40% | 67% | 66% | 62% | |
| 74.5% | 78% | 74% | 72% | 70% | 73% | 80% | |
| 74.7% | 70% | 79% | 75% | 75% | 74% | 75% | |
| 79.0% | 73% | 87% | 76% | 87% | 78% | 73% | |
| 84.5% | 86% | 87% | 81% | 86% | 83% | 84% | |
| 62.8% | 58% | 69% | 60% | 68% | 63% | 59% |