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 Australia. 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 77.0% | 2nd 76.9% | 6th 69.9% | 3rd 74.7% | 5th 70.0% | 4th 73.1% | |
| 77.5% | 82% | 77% | 87% | 78% | 61% | 80% | |
| 83.0% | 83% | 86% | 79% | 84% | 78% | 88% | |
| 79.2% | 83% | 89% | 75% | 80% | 82% | 66% | |
| 52.8% | 56% | 55% | 50% | 51% | 49% | 56% | |
| 83.3% | 89% | 84% | 74% | 84% | 80% | 89% | |
| 79.0% | 79% | 81% | 67% | 80% | 83% | 84% | |
| 77.8% | 80% | 81% | 62% | 85% | 88% | 71% | |
| 61.8% | 56% | 65% | 64% | 65% | 56% | 65% | |
| 72.5% | 76% | 78% | 78% | 67% | 67% | 69% | |
| 69.0% | 86% | 73% | 63% | 73% | 56% | 63% |