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 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 86.8% | 3rd 86.4% | 6th 82.6% | 1st 87.3% | 4th 83.8% | 5th 83.5% | |
| 86.2% | 93% | 91% | 86% | 80% | 81% | 86% | |
| 88.2% | 92% | 88% | 83% | 93% | 92% | 81% | |
| 85.3% | 79% | 88% | 89% | 85% | 91% | 80% | |
| 86.0% | 93% | 92% | 88% | 86% | 70% | 87% | |
| 86.8% | 93% | 84% | 72% | 92% | 91% | 89% | |
| 82.5% | 89% | 86% | 65% | 91% | 86% | 78% | |
| 87.0% | 90% | 85% | 84% | 90% | 86% | 87% | |
| 81.8% | 85% | 71% | 94% | 79% | 78% | 84% | |
| 87.0% | 85% | 95% | 88% | 88% | 89% | 77% | |
| 79.8% | 69% | 84% | 77% | 89% | 74% | 86% |