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 | 3rd 58.4% | 5th 53.7% | 4th 55.1% | 2nd 59.1% | 6th 44.8% | 1st 71.0% | |
| 60.3% | 56% | 78% | 64% | 71% | 23% | 70% | |
| 80.0% | 85% | 85% | 74% | 83% | 64% | 89% | |
| 63.2% | 60% | 58% | 75% | 63% | 46% | 77% | |
| 44.7% | 42% | 22% | 56% | 49% | 25% | 74% | |
| 70.0% | 74% | 71% | 58% | 78% | 69% | 70% | |
| 68.8% | 69% | 68% | 68% | 67% | 62% | 79% | |
| 6.2% | 0% | 0% | 7% | 0% | 6% | 24% | |
| 60.0% | 54% | 58% | 49% | 68% | 48% | 83% | |
| 53.2% | 60% | 38% | 45% | 56% | 46% | 74% | |
| 63.8% | 84% | 59% | 55% | 56% | 59% | 70% |