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 GD1 (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 81.2% | 5th 75.3% | 6th 73.8% | 4th 77.8% | 1st 83.3% | 3rd 78.8% | |
| 75.2% | 79% | 74% | 62% | 76% | 84% | 76% | |
| 80.8% | 82% | 69% | 78% | 81% | 92% | 83% | |
| 65.2% | 74% | 65% | 61% | 65% | 66% | 60% | |
| 92.2% | 90% | 93% | 94% | 89% | 91% | 96% |