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 Islam. 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 | 2nd 82.8% | 1st 84.4% | 6th 75.6% | 5th 82.3% | 3rd 82.6% | 4th 82.4% | |
| 84.0% | 85% | 87% | 84% | 84% | 73% | 91% | |
| 74.3% | 80% | 77% | 56% | 76% | 85% | 72% | |
| 80.8% | 82% | 81% | 62% | 89% | 86% | 85% | |
| 84.5% | 85% | 91% | 89% | 85% | 70% | 87% | |
| 82.5% | 85% | 81% | 68% | 84% | 93% | 84% | |
| 77.5% | 86% | 85% | 64% | 75% | 79% | 76% | |
| 88.2% | 88% | 85% | 92% | 92% | 84% | 88% | |
| 76.5% | 76% | 79% | 67% | 75% | 80% | 82% | |
| 86.3% | 80% | 97% | 92% | 78% | 92% | 79% | |
| 82.2% | 81% | 81% | 82% | 85% | 84% | 80% |