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 GD5 (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 82.0% | 6th 75.2% | 5th 76.6% | 1st 83.4% | 3rd 81.6% | 4th 78.5% | |
| 76.8% | 80% | 76% | 74% | 76% | 79% | 76% | |
| 87.3% | 87% | 93% | 79% | 89% | 91% | 85% | |
| 77.8% | 79% | 82% | 73% | 80% | 72% | 81% | |
| 63.3% | 94% | 0% | 62% | 91% | 68% | 65% | |
| 84.7% | 94% | 78% | 71% | 92% | 91% | 82% | |
| 71.2% | 61% | 74% | 80% | 68% | 74% | 70% | |
| 85.5% | 76% | 85% | 86% | 86% | 91% | 89% | |
| 85.5% | 88% | 92% | 84% | 93% | 87% | 69% | |
| 77.2% | 78% | 83% | 63% | 75% | 81% | 83% | |
| 86.2% | 83% | 89% | 94% | 84% | 82% | 85% |