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 | 3rd 86.9% | 1st 88.6% | 5th 83.2% | 2nd 87.6% | 6th 80.5% | 4th 84.9% | |
| 82.0% | 78% | 94% | 67% | 88% | 82% | 83% | |
| 88.7% | 88% | 96% | 96% | 83% | 93% | 76% | |
| 94.0% | 90% | 96% | 90% | 96% | 94% | 98% | |
| 76.7% | 79% | 72% | 74% | 85% | 61% | 89% | |
| 75.7% | 82% | 84% | 65% | 74% | 69% | 80% | |
| 91.7% | 98% | 89% | 92% | 92% | 86% | 93% | |
| 88.0% | 89% | 91% | 85% | 91% | 86% | 86% | |
| 78.0% | 84% | 77% | 78% | 83% | 72% | 74% | |
| 88.5% | 90% | 90% | 92% | 91% | 80% | 88% | |
| 89.7% | 91% | 97% | 93% | 93% | 82% | 82% |