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 Buddhism. 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 58.7% | 5th 51.0% | 2nd 64.0% | 4th 57.4% | 6th 38.8% | 1st 74.9% | |
| 58.8% | 60% | 52% | 77% | 60% | 34% | 70% | |
| 64.2% | 67% | 41% | 69% | 79% | 48% | 81% | |
| 53.8% | 60% | 57% | 82% | 35% | 13% | 76% | |
| 48.2% | 46% | 25% | 61% | 47% | 62% | ||
| 56.0% | 56% | 62% | 46% | 67% | 26% | 79% | |
| 73.8% | 75% | 79% | 79% | 80% | 55% | 75% | |
| 31.8% | 27% | 20% | 36% | 22% | 31% | 55% | |
| 64.7% | 73% | 58% | 74% | 64% | 50% | 69% | |
| 65.5% | 80% | 62% | 62% | 67% | 32% | 90% | |
| 53.3% | 43% | 54% | 54% | 53% | 37% | 79% |