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 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 | 1st 84.8% | 3rd 83.1% | 5th 79.0% | 2nd 83.7% | 6th 76.7% | 4th 80.4% | |
| 79.7% | 81% | 78% | 75% | 79% | 82% | 83% | |
| 85.8% | 91% | 88% | 89% | 88% | 73% | 86% | |
| 79.7% | 82% | 87% | 72% | 83% | 76% | 78% | |
| 63.3% | 68% | 65% | 56% | 81% | 50% | 60% | |
| 90.8% | 95% | 85% | 96% | 90% | 83% | 96% | |
| 79.0% | 78% | 91% | 77% | 76% | 78% | 74% | |
| 87.8% | 83% | 89% | 91% | 86% | 88% | 90% | |
| 86.3% | 95% | 84% | 84% | 88% | 77% | 90% | |
| 81.8% | 86% | 79% | 81% | 84% | 83% | 78% | |
| 78.5% | 89% | 85% | 69% | 82% | 77% | 69% |