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 Judaism. Source: Global Dialogues GD4 (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 | 6th 69.5% | 3rd 73.1% | 1st 83.0% | 2nd 74.7% | 5th 70.3% | 4th 72.0% | |
| 82.4% | 83% | 81% | 83% | 79% | 86% | ||
| 81.4% | 83% | 82% | 90% | 69% | 83% | ||
| 73.0% | 62% | 75% | 80% | 75% | |||
| 64.0% | 63% | 71% | 83% | 71% | 37% | 59% | |
| 63.6% | 51% | 80% | 55% | 70% | 62% | ||
| 81.4% | 82% | 75% | 92% | 77% | 81% | ||
| 71.2% | 74% | 53% | 74% | 74% | 81% | ||
| 64.0% | 54% | 59% | 64% | 84% | 59% | ||
| 69.6% | 66% | 79% | 66% | 71% | 66% | ||
| 72.0% | 77% | 76% | 77% | 62% | 68% |