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 Urban. Source: Global Dialogues GD6 (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 87.1% | 3rd 85.9% | - - | 4th 85.1% | 5th 79.1% | 2nd 87.0% | |
| 85.6% | 84% | 84% | 84% | 88% | 88% | ||
| 86.0% | 96% | 86% | 78% | 94% | 76% | ||
| 90.0% | 92% | 93% | 92% | 82% | 91% | ||
| 76.4% | 73% | 72% | 85% | 69% | 83% | ||
| 85.6% | 90% | 76% | 85% | 89% | 88% | ||
| 86.8% | 95% | 94% | 87% | 65% | 93% | ||
| 85.2% | 87% | 90% | 82% | 74% | 93% | ||
| 83.2% | 86% | 83% | 86% | 76% | 85% | ||
| 88.4% | 90% | 91% | 93% | 75% | 93% | ||
| 81.2% | 78% | 90% | 79% | 79% | 80% |