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 | 1st 74.4% | 6th 68.2% | 5th 68.8% | 2nd 72.3% | 4th 70.0% | 3rd 71.0% | |
| 67.2% | 67% | 75% | 56% | 69% | 69% | 67% | |
| 66.7% | 83% | 56% | 67% | 66% | 67% | 61% | |
| 71.3% | 76% | 71% | 69% | 67% | 78% | 67% | |
| 68.8% | 70% | 34% | 73% | 84% | 77% | 75% | |
| 56.8% | 66% | 58% | 56% | 54% | 50% | 57% | |
| 75.5% | 71% | 79% | 74% | 70% | 79% | 80% | |
| 73.3% | 74% | 75% | 73% | 77% | 71% | 70% | |
| 78.7% | 90% | 75% | 74% | 74% | 79% | 80% | |
| 77.2% | 78% | 76% | 76% | 83% | 72% | 78% | |
| 72.3% | 69% | 83% | 70% | 79% | 58% | 75% |