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 Suburban. Source: Global Dialogues GD4 (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 82.7% | 1st 84.8% | 6th 76.5% | 4th 80.1% | 5th 76.7% | 2nd 84.1% | |
| 81.2% | 85% | 85% | 85% | 80% | 67% | 85% | |
| 77.7% | 79% | 73% | 76% | 79% | 79% | 80% | |
| 88.3% | 92% | 89% | 84% | 83% | 87% | 95% | |
| 88.0% | 91% | 89% | 85% | 81% | 91% | 91% | |
| 86.8% | 86% | 91% | 79% | 88% | 91% | 86% | |
| 85.2% | 94% | 93% | 88% | 86% | 64% | 86% | |
| 49.8% | 48% | 63% | 49% | 51% | 38% | 50% | |
| 86.0% | 90% | 90% | 77% | 87% | 82% | 90% | |
| 79.8% | 75% | 83% | 67% | 76% | 88% | 90% | |
| 85.3% | 87% | 92% | 75% | 90% | 80% | 88% |