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 | 2nd 82.6% | 1st 85.3% | 6th 76.9% | 3rd 81.9% | 5th 78.6% | 4th 78.9% | |
| 78.0% | 83% | 81% | 60% | 80% | 82% | 82% | |
| 85.0% | 87% | 87% | 80% | 90% | 82% | 84% | |
| 76.3% | 83% | 78% | 79% | 76% | 64% | 78% | |
| 72.2% | 75% | 79% | 65% | 81% | 64% | 69% | |
| 85.2% | 87% | 98% | 75% | 82% | 87% | 82% | |
| 75.8% | 74% | 78% | 78% | 82% | 74% | 69% | |
| 86.3% | 80% | 91% | 89% | 80% | 91% | 87% | |
| 86.3% | 86% | 87% | 81% | 91% | 88% | 85% | |
| 79.0% | 78% | 88% | 77% | 73% | 78% | 80% | |
| 82.8% | 93% | 86% | 85% | 84% | 76% | 73% |