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 GD7 (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 73.3% | 1st 73.7% | 6th 65.7% | 2nd 73.5% | 5th 68.7% | 4th 70.5% | |
| 52.7% | 59% | 55% | 50% | 55% | 49% | 48% | |
| 67.2% | 78% | 77% | 47% | 73% | 61% | 67% | |
| 88.3% | 81% | 94% | 88% | 81% | 96% | 90% | |
| 67.5% | 67% | 64% | 75% | 67% | 60% | 72% | |
| 71.7% | 76% | 72% | 62% | 78% | 73% | 69% | |
| 76.2% | 84% | 83% | 68% | 78% | 70% | 74% | |
| 70.8% | 75% | 70% | 61% | 77% | 73% | 69% | |
| 79.3% | 81% | 83% | 65% | 83% | 81% | 83% | |
| 66.2% | 68% | 70% | 75% | 62% | 60% | 62% | |
| 69.2% | 64% | 69% | 66% | 81% | 64% | 71% |