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 Other religious group. Source: Global Dialogues GD5 (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 | 3rd 69.3% | 4th 68.3% | 5th 66.0% | 2nd 71.3% | 6th 65.0% | 1st 71.5% | |
| 66.8% | 62% | 66% | 53% | 74% | 63% | 83% | |
| 60.0% | 65% | 70% | 51% | 56% | 53% | 65% | |
| 54.7% | 59% | 57% | 43% | 57% | 57% | 55% | |
| 80.3% | 75% | 76% | 87% | 96% | 69% | 79% | |
| 75.2% | 87% | 55% | 76% | 78% | 82% | 73% | |
| 57.3% | 54% | 64% | 62% | 62% | 43% | 59% | |
| 86.8% | 91% | 81% | 68% | 95% | 88% | 98% | |
| 73.3% | 77% | 74% | 71% | 69% | 73% | 76% | |
| 50.3% | 50% | 54% | 52% | 49% | 45% | 52% | |
| 80.8% | 73% | 86% | 97% | 77% | 77% | 75% |