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 Male. 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 68.8% | 5th 63.0% | 4th 65.9% | 2nd 72.3% | 6th 45.5% | 1st 84.9% | |
| 70.2% | 74% | 71% | 66% | 79% | 44% | 87% | |
| 80.7% | 83% | 86% | 83% | 81% | 72% | 79% | |
| 72.2% | 67% | 66% | 72% | 89% | 49% | 90% | |
| 63.8% | 84% | 57% | 56% | 70% | 29% | 87% | |
| 64.8% | 78% | 69% | 50% | 79% | 30% | 83% | |
| 68.7% | 67% | 65% | 67% | 67% | 61% | 85% | |
| 39.5% | 26% | 20% | 67% | 22% | 29% | 73% | |
| 67.0% | 62% | 66% | 58% | 92% | 41% | 83% | |
| 73.3% | 77% | 59% | 83% | 71% | 57% | 93% | |
| 67.2% | 70% | 71% | 57% | 73% | 43% | 89% |