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 | 3rd 87.3% | 1st 90.0% | 6th 80.1% | 2nd 87.9% | 5th 81.2% | 4th 86.9% | |
| 87.0% | 92% | 91% | 81% | 87% | 77% | 94% | |
| 84.5% | 92% | 83% | 70% | 93% | 87% | 82% | |
| 87.8% | 85% | 97% | 85% | 84% | 88% | 88% | |
| 88.3% | 90% | 96% | 84% | 90% | 79% | 91% | |
| 84.7% | 86% | 86% | 73% | 91% | 80% | 92% | |
| 82.5% | 87% | 86% | 73% | 87% | 82% | 80% | |
| 85.3% | 87% | 91% | 86% | 83% | 75% | 90% | |
| 82.2% | 86% | 88% | 79% | 85% | 73% | 82% | |
| 86.7% | 82% | 95% | 87% | 88% | 86% | 82% | |
| 86.7% | 86% | 87% | 83% | 91% | 85% | 88% |