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 | 5th 65.9% | 4th 66.0% | 2nd 67.3% | 3rd 67.1% | 5th 65.9% | 1st 73.4% | |
| 70.5% | 67% | 78% | 62% | 68% | 78% | 70% | |
| 79.2% | 80% | 78% | 76% | 71% | 81% | 89% | |
| 57.8% | 54% | 66% | 71% | 45% | 42% | 69% | |
| 61.5% | 62% | 48% | 52% | 68% | 79% | 60% | |
| 60.2% | 61% | 65% | 38% | 69% | 62% | 66% | |
| 71.0% | 65% | 72% | 76% | 76% | 61% | 76% | |
| 66.2% | 61% | 62% | 76% | 57% | 65% | 76% | |
| 60.8% | 51% | 57% | 69% | 56% | 59% | 73% | |
| 72.5% | 79% | 63% | 80% | 81% | 55% | 77% | |
| 76.3% | 79% | 71% | 73% | 80% | 77% | 78% |