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 [synth]: Predict response distributions for Christianity. Source: Global Dialogues GD4 (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 | 4th 56.8% | 5th 52.4% | 3rd 61.8% | 2nd 67.9% | 6th 51.1% | 1st 82.7% | |
| 68.5% | 61% | 73% | 82% | 80% | 39% | 76% | |
| 66.7% | 70% | 45% | 66% | 75% | 70% | 74% | |
| 72.3% | 67% | 61% | 71% | 95% | 51% | 89% | |
| 52.7% | 47% | 31% | 57% | 53% | 40% | 88% | |
| 69.3% | 57% | 67% | 54% | 81% | 69% | 88% | |
| 63.5% | 60% | 60% | 61% | 61% | 47% | 92% | |
| 35.5% | 26% | 9% | 47% | 33% | 35% | 63% | |
| 67.0% | 62% | 62% | 65% | 70% | 59% | 84% | |
| 57.0% | 59% | 44% | 40% | 56% | 59% | 84% | |
| 68.7% | 59% | 72% | 75% | 75% | 42% | 89% |