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 77.5% | 4th 73.2% | 5th 71.2% | 3rd 74.3% | 6th 70.3% | 2nd 74.9% | |
| 62.7% | 66% | 56% | 64% | 63% | 56% | 71% | |
| 62.5% | 71% | 66% | 45% | 66% | 62% | 65% | |
| 77.3% | 72% | 83% | 79% | 76% | 75% | 79% | |
| 72.2% | 83% | 64% | 70% | 74% | 61% | 81% | |
| 79.3% | 79% | 74% | 81% | 79% | 84% | 79% | |
| 81.5% | 94% | 82% | 66% | 83% | 88% | 76% | |
| 73.5% | 75% | 86% | 84% | 72% | 52% | 72% | |
| 65.8% | 67% | 71% | 57% | 69% | 65% | 66% | |
| 82.0% | 86% | 72% | 84% | 77% | 87% | 86% | |
| 78.8% | 82% | 78% | 82% | 84% | 73% | 74% |