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 | 4th 85.5% | 1st 87.8% | 6th 82.9% | 3rd 87.4% | 2nd 87.7% | 5th 85.3% | |
| 82.5% | 86% | 84% | 88% | 72% | 79% | 86% | |
| 86.5% | 91% | 95% | 62% | 93% | 97% | 81% | |
| 87.0% | 83% | 88% | 86% | 95% | 91% | 79% | |
| 89.8% | 90% | 85% | 87% | 88% | 94% | 95% | |
| 86.8% | 87% | 90% | 73% | 90% | 92% | 89% | |
| 84.8% | 89% | 84% | 78% | 90% | 90% | 78% | |
| 89.0% | 90% | 88% | 90% | 90% | 89% | 87% | |
| 83.2% | 86% | 86% | 87% | 79% | 78% | 83% | |
| 88.8% | 87% | 93% | 92% | 89% | 86% | 86% | |
| 82.5% | 66% | 85% | 86% | 88% | 81% | 89% |