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 Female. 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 59.5% | 5th 49.6% | 2nd 68.3% | 3rd 64.7% | 6th 47.6% | 1st 79.6% | |
| 70.8% | 60% | 79% | 84% | 76% | 47% | 79% | |
| 72.5% | 76% | 58% | 75% | 76% | 70% | 80% | |
| 63.2% | 65% | 38% | 82% | 83% | 35% | 76% | |
| 56.0% | 55% | 50% | 52% | 52% | 46% | 81% | |
| 63.8% | 59% | 42% | 79% | 69% | 51% | 83% | |
| 71.3% | 71% | 71% | 87% | 70% | 51% | 78% | |
| 25.0% | 16% | 5% | 27% | 16% | 27% | 59% | |
| 66.8% | 56% | 57% | 79% | 78% | 46% | 85% | |
| 62.5% | 77% | 36% | 56% | 65% | 50% | 91% | |
| 63.5% | 60% | 60% | 62% | 62% | 53% | 84% |