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 Judaism. 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 52.5% | 5th 48.7% | 2nd 55.7% | 3rd 53.3% | 6th 31.9% | 1st 70.7% | |
| 64.5% | 57% | 77% | 82% | 75% | 29% | 67% | |
| 73.3% | 81% | 89% | 70% | 78% | 34% | 88% | |
| 53.2% | 50% | 57% | 76% | 45% | 15% | 76% | |
| 37.7% | 39% | 10% | 52% | 26% | 25% | 74% | |
| 67.5% | 60% | 70% | 61% | 71% | 69% | 74% | |
| 66.5% | 69% | 69% | 66% | 67% | 54% | 74% | |
| 6.5% | 0% | 0% | 7% | 0% | 6% | 26% | |
| 53.5% | 50% | 48% | 55% | 59% | 29% | 80% | |
| 43.0% | 60% | 15% | 33% | 58% | 15% | 77% | |
| 55.7% | 59% | 52% | 55% | 54% | 43% | 71% |