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 | 2nd 87.1% | 1st 87.5% | 5th 81.2% | 4th 84.5% | 6th 79.0% | 3rd 85.9% | |
| 87.5% | 84% | 97% | 84% | 84% | 88% | 88% | |
| 83.0% | 96% | 86% | 70% | 79% | 92% | 75% | |
| 89.3% | 92% | 93% | 86% | 92% | 82% | 91% | |
| 79.3% | 73% | 72% | 81% | 85% | 76% | 89% | |
| 80.2% | 90% | 76% | 66% | 84% | 88% | 77% | |
| 87.2% | 95% | 94% | 92% | 87% | 67% | 88% | |
| 83.5% | 87% | 88% | 84% | 82% | 72% | 88% | |
| 81.0% | 86% | 85% | 76% | 83% | 71% | 85% | |
| 87.2% | 90% | 92% | 77% | 92% | 75% | 97% | |
| 83.8% | 78% | 92% | 96% | 77% | 79% | 81% |