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 GD3 (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 | 1st 74.2% | 4th 69.8% | - - | 3rd 72.2% | 5th 64.5% | 2nd 73.4% | |
| 70.2% | 69% | 80% | 62% | 77% | 63% | ||
| 61.8% | 71% | 78% | 57% | 46% | 57% | ||
| 82.6% | 84% | 82% | 81% | 83% | 83% | ||
| 83.8% | 84% | 83% | 82% | 88% | 82% | ||
| 50.2% | 53% | 56% | 47% | 31% | 64% | ||
| 72.6% | 72% | 71% | 75% | 73% | 72% | ||
| 76.2% | 80% | 76% | 80% | 65% | 80% | ||
| 70.2% | 74% | 71% | 73% | 54% | 79% | ||
| 71.2% | 88% | 43% | 90% | 56% | 79% | ||
| 69.4% | 67% | 58% | 75% | 72% | 75% |