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: Predict response distributions for Male. Source: Global Dialogues GD7 (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 | 1st 89.3% | 2nd 88.5% | 6th 80.5% | 3rd 86.0% | 5th 83.7% | 4th 85.5% | |
| 87.5% | 90% | 93% | 90% | 80% | 80% | 92% | |
| 84.0% | 94% | 93% | 62% | 97% | 77% | 81% | |
| 81.0% | 82% | 81% | 81% | 78% | 86% | 78% | |
| 87.8% | 93% | 90% | 89% | 86% | 80% | 89% | |
| 91.0% | 93% | 90% | 85% | 93% | 92% | 93% | |
| 85.0% | 91% | 88% | 71% | 88% | 89% | 83% | |
| 86.0% | 88% | 86% | 83% | 90% | 84% | 85% | |
| 78.0% | 75% | 82% | 79% | 78% | 69% | 85% | |
| 88.7% | 93% | 90% | 86% | 86% | 93% | 84% | |
| 86.8% | 94% | 92% | 79% | 84% | 87% | 85% |