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 Canada. 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 | 2nd 77.1% | 1st 79.4% | 6th 73.7% | 5th 74.3% | 3rd 74.9% | 4th 74.9% | |
| 76.3% | 71% | 87% | 70% | 74% | 77% | 79% | |
| 69.3% | 75% | 76% | 51% | 72% | 75% | 67% | |
| 83.5% | 84% | 98% | 91% | 83% | 74% | 71% | |
| 86.5% | 89% | 80% | 83% | 86% | 86% | 95% | |
| 71.2% | 72% | 74% | 77% | 71% | 68% | 65% | |
| 68.7% | 78% | 73% | 60% | 66% | 65% | 70% | |
| 80.0% | 86% | 80% | 83% | 70% | 77% | 84% | |
| 74.2% | 75% | 73% | 80% | 74% | 71% | 72% | |
| 71.2% | 65% | 77% | 66% | 73% | 77% | 69% | |
| 76.8% | 76% | 76% | 76% | 79% | 77% |