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 Suburban. 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 | 4th 82.1% | 1st 84.4% | 5th 80.6% | 2nd 83.9% | 6th 80.6% | 3rd 83.5% | |
| 76.3% | 81% | 71% | 80% | 79% | 76% | 71% | |
| 87.5% | 87% | 93% | 89% | 89% | 82% | 85% | |
| 81.2% | 82% | 81% | 78% | 80% | 80% | 86% | |
| 82.5% | 82% | 96% | 74% | 91% | 67% | 85% | |
| 87.5% | 88% | 83% | 91% | 90% | 91% | 82% | |
| 71.3% | 66% | 75% | 63% | 78% | 73% | 73% | |
| 86.7% | 76% | 85% | 82% | 91% | 97% | 89% | |
| 87.3% | 89% | 88% | 91% | 81% | 87% | 88% | |
| 75.7% | 82% | 78% | 64% | 79% | 64% | 87% | |
| 89.2% | 88% | 94% | 94% | 81% | 89% | 89% |