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 GD6 (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 68.9% | 4th 66.8% | 5th 63.8% | 3rd 68.8% | 6th 62.7% | 1st 70.7% | |
| 73.0% | 69% | 80% | 60% | 78% | 78% | 73% | |
| 60.8% | 71% | 66% | 49% | 54% | 66% | 59% | |
| 58.2% | 65% | 57% | 50% | 66% | 44% | 67% | |
| 75.7% | 74% | 72% | 77% | 77% | 77% | 77% | |
| 62.7% | 69% | 63% | 45% | 63% | 71% | 65% | |
| 65.7% | 67% | 72% | 65% | 66% | 48% | 76% | |
| 64.2% | 66% | 62% | 64% | 70% | 53% | 70% | |
| 59.8% | 51% | 58% | 69% | 57% | 54% | 70% | |
| 70.8% | 78% | 66% | 78% | 76% | 55% | 72% | |
| 78.7% | 79% | 72% | 81% | 81% | 81% | 78% |